{"license":"CC BY-SA 4.0","license_file":"https://deskgpu.com/data/LICENSE.txt","attribution":"https://deskgpu.com/data/attribution.json","build":"04bba6e6e4-20261019T0139","estimate":true,"engine":"llama.cpp 5aeac37a, GGUF, all layers on the GPU, Flash Attention on, n_ubatch 512, F16 KV cache; fits judged with 4 parallel sequences (unified KV), doesn't fit judged with 1; idle device","context":"min(8192, model maximum)","definitions":{"verdict":"fits = llama.cpp default --fit load check passes with the estimate margin (not a promise about runtime peak memory); tight = within the estimate error range; no = does not fit even with the whole memory, at every quantization; na = unknown (see unknown_reason): only need_gib is given","unknown_reason":"no_profile = no run profile covers this device; no_measured_total = workstation or data-center GPU: public logs do not establish its memory configuration (for example whether ECC is on), so fits and tight are not judged whether or not a total was measured for the model (code name kept for compatibility); capacity_too_small = less than 2 GiB is counted as available after the profile reserve, below the threshold for judging. Unknown devices still get \"no\" when the model does not fit even in the whole memory at every quantization","quant":"fits: highest quantization that fits; tight: highest borderline quantization; no / na: the quantization with the fewest bytes on the GPU","need_gib":"X = max over cards of (buffers / 0.95 + 1 GiB): available memory per card needed for \"fits\"","max_context_capped":"true = still fits at the longest context covered by measured logs; longer contexts were not checked","identical_cards":"only when one card does not fit: N = smallest N in 2..8 that fits with the default even split; \"8:tight\" = borderline with 8 cards; \"over\" = does not fit with 8 cards (the only value given for devices whose verdict is otherwise unknown: workstation and data-center GPUs, and GPUs with less than 2 GiB available)"},"columns":["gpu","model","profile","verdict","quant","context","need_gib","max_context","max_context_capped","tps_ceiling","identical_cards","unknown_reason"],"rows":[["amd-instinct-mi210","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","baichuan-m3-235b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,null,null],["amd-instinct-mi210","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-instinct-mi210","command-a-plus-05-2026-bf16","rocm","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-instinct-mi210","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-instinct-mi210","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-instinct-mi210","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-instinct-mi210","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-instinct-mi210","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,null,null],["amd-instinct-mi210","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-instinct-mi210","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,null,null],["amd-instinct-mi210","glm-4-7-reap-268b-a32b","rocm","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-instinct-mi210","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["amd-instinct-mi210","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-instinct-mi210","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-instinct-mi210","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,null,null],["amd-instinct-mi210","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["amd-instinct-mi210","gpt-oss-120b","rocm","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo2-235b-a22b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["amd-instinct-mi210","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["amd-instinct-mi210","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,null,null],["amd-instinct-mi210","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-instinct-mi210","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-instinct-mi210","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-instinct-mi210","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-instinct-mi210","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,null,null],["amd-instinct-mi210","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-instinct-mi210","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi210","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,null,null],["amd-instinct-mi210","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-instinct-mi210","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-instinct-mi210","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-instinct-mi210","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","minimax-m2-7","rocm","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-instinct-mi210","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,null,null],["amd-instinct-mi210","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,null,null],["amd-instinct-mi210","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-instinct-mi210","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,null,null],["amd-instinct-mi210","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-instinct-mi210","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,null,null],["amd-instinct-mi210","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,null,null],["amd-instinct-mi210","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-nemotron-235b-a22b-genrm","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-instinct-mi210","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["amd-instinct-mi210","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-instinct-mi210","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["amd-instinct-mi210","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-instinct-mi210","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi210","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","baichuan-m3-235b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,null,null],["amd-instinct-mi300x","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-instinct-mi300x","command-a-plus-05-2026-bf16","rocm","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-instinct-mi300x","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-instinct-mi300x","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-instinct-mi300x","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-instinct-mi300x","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-5","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-6-reap-268b-a32b","rocm","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-7","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-7-reap-218b-a32b","rocm","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-4-7-reap-268b-a32b","rocm","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-instinct-mi300x","glm-5-1","rocm","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi300x","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi300x","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,null,null],["amd-instinct-mi300x","glm-5-3-flash-bf16","rocm","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gpt-oss-120b","rocm","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo2-235b-a22b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","hy3","rocm","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","intern-s2-397b","rocm","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","k-exaone-236b-a23b","rocm","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-instinct-mi300x","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-instinct-mi300x","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-instinct-mi300x","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-instinct-mi300x","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","laguna-s-2-1","rocm","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-instinct-mi300x","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-v2-5","rocm","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-instinct-mi300x","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-v2-6-flash-mopd","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-v2-6-flash-rl","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi300x","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi300x","mimo-v2-flash","rocm","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minimax-m2","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minimax-m2-1","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minimax-m2-5","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","minimax-m2-7","rocm","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-instinct-mi300x","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,null,null],["amd-instinct-mi300x","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-235b-a22b","rocm","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-235b-a22b-instruct-2507","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-397b-a17b","rocm","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-instinct-mi300x","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-480b-a35b-instruct","rocm","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-coder-reap-363b-a35b","rocm","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-nemotron-235b-a22b-genrm","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-235b-a22b-instruct","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","step-3-7-flash","rocm","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-large-base","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-large-thinking","rocm","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-large-truebase","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi300x","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","baichuan-m3-235b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,null,null],["amd-instinct-mi325x","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","cogito-671b-v2-1","rocm","na","Q2_K",8192,242.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","command-a-plus-05-2026-bf16","rocm","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1","rocm","na","Q2_K",8192,280.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-v3","rocm","na","Q2_K",8192,257.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-v3-1","rocm","na","Q2_K",8192,242.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","deepseek-v3-2","rocm","na","Q2_K",8192,242.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-5","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-6-reap-268b-a32b","rocm","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-7","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-7-reap-218b-a32b","rocm","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-4-7-reap-268b-a32b","rocm","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-5","rocm","na","Q2_K",8192,268.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-5-1","rocm","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi325x","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi325x","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,null,null],["amd-instinct-mi325x","glm-5-3-flash-bf16","rocm","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gpt-oss-120b","rocm","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo2-235b-a22b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","hy3","rocm","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","intern-s2-397b","rocm","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","k-exaone-236b-a23b","rocm","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-instinct-mi325x","kimi-k2-6","rocm","na","IQ2_XXS",8192,267.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-instinct-mi325x","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-instinct-mi325x","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","laguna-s-2-1","rocm","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-instinct-mi325x","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-5","rocm","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-5-pro","rocm","na","IQ2_XXS",8192,270.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-6-flash-mopd","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-6-flash-rl","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi325x","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi325x","mimo-v2-flash","rocm","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minimax-m2","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minimax-m2-1","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minimax-m2-5","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","minimax-m2-7","rocm","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-large-3-675b-instruct-2512","rocm","na","Q2_K",8192,243.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,null,null],["amd-instinct-mi325x","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-235b-a22b","rocm","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-235b-a22b-instruct-2507","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-397b-a17b","rocm","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-instinct-mi325x","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-480b-a35b-instruct","rocm","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-coder-reap-363b-a35b","rocm","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-nemotron-235b-a22b-genrm","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-235b-a22b-instruct","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","step-3-7-flash","rocm","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-large-base","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-large-thinking","rocm","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-large-truebase","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi325x","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","baichuan-m3-235b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,null,null],["amd-instinct-mi355x","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","cogito-671b-v2-1","rocm","na","Q2_K",8192,242.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","command-a-plus-05-2026-bf16","rocm","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1","rocm","na","Q2_K",8192,280.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-v3","rocm","na","Q2_K",8192,257.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-v3-1","rocm","na","Q2_K",8192,242.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","deepseek-v3-2","rocm","na","Q2_K",8192,242.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-5","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-6-reap-268b-a32b","rocm","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-7","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-7-reap-218b-a32b","rocm","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-4-7-reap-268b-a32b","rocm","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-5","rocm","na","Q2_K",8192,268.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-5-1","rocm","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi355x","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-instinct-mi355x","glm-5-3-flash","rocm","na","Q8_0",8192,327.9,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","glm-5-3-flash-bf16","rocm","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gpt-oss-120b","rocm","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo2-235b-a22b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","hy3","rocm","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","intern-s2-397b","rocm","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","k-exaone-236b-a23b","rocm","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-instinct-mi355x","kimi-k2-6","rocm","na","IQ2_XXS",8192,267.64,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-instinct-mi355x","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-instinct-mi355x","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","laguna-s-2-1","rocm","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-instinct-mi355x","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-5","rocm","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-5-pro","rocm","na","IQ2_XXS",8192,270.42,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-6-flash-mopd","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-6-flash-rl","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi355x","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-instinct-mi355x","mimo-v2-flash","rocm","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minimax-m2","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minimax-m2-1","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minimax-m2-5","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","minimax-m2-7","rocm","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-large-3-675b-instruct-2512","rocm","na","Q2_K",8192,243.79,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","muse-spark-open-816b-a42b","rocm","na","Q2_K",8192,301.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-235b-a22b","rocm","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-235b-a22b-instruct-2507","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-397b-a17b","rocm","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,null,null],["amd-instinct-mi355x","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-480b-a35b-instruct","rocm","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-coder-reap-363b-a35b","rocm","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-nemotron-235b-a22b-genrm","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-235b-a22b-instruct","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","step-3-7-flash","rocm","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-large-base","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-large-thinking","rocm","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-large-truebase","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-instinct-mi355x","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-mi350x","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-mi350x","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-mi350x","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-mi350x","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-mi350x","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-mi350x","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-mi350x","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-mi350x","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-mi350x","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-mi350x","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-mi350x","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-mi350x","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-mi350x","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-mi350x","baichuan-m3-235b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-mi350x","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,null,null],["amd-mi350x","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-mi350x","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-mi350x","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-mi350x","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","cogito-671b-v2-1","rocm","na","Q2_K",8192,242.4,null,null,null,null,"no_measured_total"],["amd-mi350x","command-a-plus-05-2026-bf16","rocm","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["amd-mi350x","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-mi350x","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-mi350x","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-mi350x","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1","rocm","na","Q2_K",8192,280.34,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-v3","rocm","na","Q2_K",8192,257.8,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-v3-1","rocm","na","Q2_K",8192,242.41,null,null,null,null,"no_measured_total"],["amd-mi350x","deepseek-v3-2","rocm","na","Q2_K",8192,242.08,null,null,null,null,"no_measured_total"],["amd-mi350x","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-mi350x","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-mi350x","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-mi350x","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-mi350x","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-mi350x","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-mi350x","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-mi350x","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-mi350x","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-mi350x","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-mi350x","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-mi350x","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-mi350x","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-mi350x","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-mi350x","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-mi350x","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-mi350x","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-5","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-6-reap-268b-a32b","rocm","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-7","rocm","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-7-reap-218b-a32b","rocm","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-4-7-reap-268b-a32b","rocm","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-5","rocm","na","Q2_K",8192,268.86,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-5-1","rocm","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-mi350x","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,null,null],["amd-mi350x","glm-5-3-flash","rocm","na","Q8_0",8192,327.9,null,null,null,null,"no_measured_total"],["amd-mi350x","glm-5-3-flash-bf16","rocm","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["amd-mi350x","gpt-oss-120b","rocm","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["amd-mi350x","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-mi350x","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-mi350x","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-mi350x","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-mi350x","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-mi350x","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-mi350x","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-mi350x","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-mi350x","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-mi350x","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-mi350x","holo2-235b-a22b","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-mi350x","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-mi350x","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-mi350x","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-mi350x","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-mi350x","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-mi350x","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-mi350x","hy3","rocm","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["amd-mi350x","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","intern-s2-397b","rocm","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["amd-mi350x","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-mi350x","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-mi350x","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-mi350x","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-mi350x","k-exaone-236b-a23b","rocm","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["amd-mi350x","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-mi350x","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-mi350x","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-mi350x","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-mi350x","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-mi350x","kimi-k2-6","rocm","na","IQ2_XXS",8192,267.64,null,null,null,null,"no_measured_total"],["amd-mi350x","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-mi350x","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-mi350x","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-mi350x","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-mi350x","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-mi350x","laguna-s-2-1","rocm","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["amd-mi350x","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-mi350x","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-mi350x","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-mi350x","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-mi350x","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-mi350x","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-mi350x","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-mi350x","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-mi350x","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-mi350x","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-mi350x","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-5","rocm","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-5-pro","rocm","na","IQ2_XXS",8192,270.42,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-6-flash-mopd","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-6-flash-rl","rocm","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["amd-mi350x","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-mi350x","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-mi350x","mimo-v2-flash","rocm","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-mi350x","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-mi350x","minimax-m2","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-mi350x","minimax-m2-1","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-mi350x","minimax-m2-5","rocm","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["amd-mi350x","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-mi350x","minimax-m2-7","rocm","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-mi350x","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-large-3-675b-instruct-2512","rocm","na","Q2_K",8192,243.79,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-mi350x","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-mi350x","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-mi350x","muse-spark-open-816b-a42b","rocm","na","Q2_K",8192,301.03,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-mi350x","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-mi350x","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-mi350x","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-mi350x","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-mi350x","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-mi350x","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-mi350x","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-mi350x","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-235b-a22b","rocm","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-235b-a22b-instruct-2507","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-397b-a17b","rocm","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,null,null],["amd-mi350x","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-480b-a35b-instruct","rocm","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-coder-reap-363b-a35b","rocm","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-nemotron-235b-a22b-genrm","rocm","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-235b-a22b-instruct","rocm","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-mi350x","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-mi350x","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-mi350x","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-mi350x","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-mi350x","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-mi350x","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-mi350x","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-mi350x","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-mi350x","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-mi350x","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-mi350x","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-mi350x","step-3-7-flash","rocm","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["amd-mi350x","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-mi350x","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-mi350x","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-mi350x","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-mi350x","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-mi350x","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-mi350x","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-large-base","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-large-thinking","rocm","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-large-truebase","rocm","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-mi350x","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-mi350x","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-mi350x","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-mi350x","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-mi350x","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-mi350x","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-mi350x","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-mi350x","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-mi350x","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-mi350x","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-mi350x","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-mi350x","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-mi350x","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-mi350x","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-ai-pro-r9700","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-radeon-ai-pro-r9700","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["amd-radeon-ai-pro-r9700","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-radeon-ai-pro-r9700","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-radeon-ai-pro-r9700","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-radeon-ai-pro-r9700","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-radeon-ai-pro-r9700","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-ai-pro-r9700","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["amd-radeon-ai-pro-r9700","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["amd-radeon-ai-pro-r9700","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,null,null],["amd-radeon-ai-pro-r9700","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-ai-pro-r9700","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["amd-radeon-ai-pro-r9700","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["amd-radeon-ai-pro-r9700","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,null,null],["amd-radeon-ai-pro-r9700","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-radeon-ai-pro-r9700","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,null,null],["amd-radeon-ai-pro-r9700","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,null,null],["amd-radeon-ai-pro-r9700","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-ai-pro-r9700","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-ai-pro-r9700","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-ai-pro-r9700","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["amd-radeon-ai-pro-r9700","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["amd-radeon-ai-pro-r9700","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-ai-pro-r9700","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,null,null],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["amd-radeon-ai-pro-r9700","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["amd-radeon-ai-pro-r9700","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-ai-pro-r9700","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-ai-pro-r9700","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["amd-radeon-ai-pro-r9700","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["amd-radeon-ai-pro-r9700","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["amd-radeon-ai-pro-r9700","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-ai-pro-r9700","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["amd-radeon-ai-pro-r9700","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-ai-pro-r9700","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-ai-pro-r9700","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","aescode-32b","rocm","no","IQ2_XXS",8192,13.6,null,null,null,null,null],["amd-radeon-pro-v520","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ai21-jamba2-mini","rocm","no","IQ2_XXS",8192,13.63,null,null,null,null,null],["amd-radeon-pro-v520","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-v520","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-pro-v520","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-pro-v520","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["amd-radeon-pro-v520","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","cosmos-reason2-32b","rocm","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["amd-radeon-pro-v520","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-pro-v520","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,null,null],["amd-radeon-pro-v520","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","deepseek-r1-distill-qwen-32b","rocm","no","Q2_K",8192,15.24,null,null,null,null,null],["amd-radeon-pro-v520","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-pro-v520","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-pro-v520","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-pro-v520","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-pro-v520","devstral-small-2-24b-instruct-2512","rocm","no","Q2_K",8192,11.09,null,null,null,null,null],["amd-radeon-pro-v520","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","eurollm-22b-instruct-2512","rocm","no","IQ2_M",8192,10.57,null,null,null,null,null],["amd-radeon-pro-v520","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","exaone-4-5-33b","rocm","no","IQ4_XS",8192,20.43,null,null,null,null,null],["amd-radeon-pro-v520","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","fara1-5-27b","rocm","no","IQ2_M",8192,12.54,null,null,null,null,null],["amd-radeon-pro-v520","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","frogboss-32b-2510","rocm","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["amd-radeon-pro-v520","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-2-27b-it","rocm","no","IQ2_M",8192,13.78,null,null,null,null,null],["amd-radeon-pro-v520","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-3-27b-it","rocm","no","Q2_K",8192,14.43,null,null,null,null,null],["amd-radeon-pro-v520","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-4-12b","rocm","no","Q8_0",8192,15.57,null,null,null,null,null],["amd-radeon-pro-v520","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-4-26b-a4b","rocm","no","Q2_K",8192,13,null,null,null,null,null],["amd-radeon-pro-v520","gemma-4-26b-a4b-it","rocm","no","IQ2_XXS",8192,12.09,null,null,null,null,null],["amd-radeon-pro-v520","gemma-4-31b","rocm","no","Q2_K",8192,17.58,null,null,null,null,null],["amd-radeon-pro-v520","gemma-4-31b-it","rocm","no","Q3_K_M",8192,20.34,null,null,null,null,null],["amd-radeon-pro-v520","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"over",null],["amd-radeon-pro-v520","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-pro-v520","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["amd-radeon-pro-v520","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"over",null],["amd-radeon-pro-v520","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-pro-v520","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"over",null],["amd-radeon-pro-v520","glm-4-7-flash","rocm","no","Q2_K",8192,12.77,null,null,null,null,null],["amd-radeon-pro-v520","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"over",null],["amd-radeon-pro-v520","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-pro-v520","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["amd-radeon-pro-v520","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,null,null],["amd-radeon-pro-v520","gpt-oss-20b","rocm","no","Q2_K",8192,12.56,null,null,null,null,null],["amd-radeon-pro-v520","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-1-30b","rocm","no","Q2_K",8192,13.89,null,null,null,null,null],["amd-radeon-pro-v520","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-2-30b","rocm","no","Q2_K",8192,13.89,null,null,null,null,null],["amd-radeon-pro-v520","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","hermes-4-3-36b","rocm","no","IQ2_XXS",8192,12.89,null,null,null,null,null],["amd-radeon-pro-v520","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo-3-1-35b-a3b","rocm","no","Q2_K",8192,14.45,null,null,null,null,null],["amd-radeon-pro-v520","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-v520","holo2-30b-a3b","rocm","no","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-pro-v520","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo3-35b-a3b","rocm","no","Q2_K",8192,14.45,null,null,null,null,null],["amd-radeon-pro-v520","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","holo4-35b-a3b","rocm","no","IQ2_XXS",8192,11.98,null,null,null,null,null],["amd-radeon-pro-v520","holotron4-30b-a3b","rocm","no","IQ2_M",8192,18.88,null,null,null,null,null],["amd-radeon-pro-v520","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["amd-radeon-pro-v520","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["amd-radeon-pro-v520","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["amd-radeon-pro-v520","ising-calibration-1-35b-a3b","rocm","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["amd-radeon-pro-v520","ising-calibration-1-5-31b-bf16","rocm","no","IQ2_XXS",8192,16.51,null,null,null,null,null],["amd-radeon-pro-v520","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["amd-radeon-pro-v520","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","kat-coder-v2-5-dev","rocm","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["amd-radeon-pro-v520","kat-dev-72b-exp","rocm","no","IQ2_XXS",8192,28.54,null,null,null,null,null],["amd-radeon-pro-v520","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-pro-v520","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-pro-v520","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-pro-v520","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-pro-v520","kimi-linear-48b-a3b-base","rocm","no","IQ2_XXS",8192,14.24,null,null,null,null,null],["amd-radeon-pro-v520","kimi-linear-48b-a3b-instruct","rocm","no","IQ2_XXS",8192,13.35,null,null,null,null,null],["amd-radeon-pro-v520","kimi-linear-reap-35b-a3b-instruct","rocm","no","IQ2_XXS",8192,10.67,null,null,null,null,null],["amd-radeon-pro-v520","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["amd-radeon-pro-v520","laguna-xs-2-1","rocm","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["amd-radeon-pro-v520","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-24b-a2b","rocm","no","Q4_0",8192,14.65,null,null,null,null,null],["amd-radeon-pro-v520","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-24b-a2b","rocm","no","Q4_0",8192,14.75,null,null,null,null,null],["amd-radeon-pro-v520","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-pro-v520","llama-3-1-70b-instruct","rocm","no","IQ2_XXS",8192,22.29,null,null,null,null,null],["amd-radeon-pro-v520","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,null,null],["amd-radeon-pro-v520","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,null,null],["amd-radeon-pro-v520","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-pro-v520","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"over",null],["amd-radeon-pro-v520","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm-v-4-7-35b-a3b","rocm","no","IQ4_XS",8192,20.02,null,null,null,null,null],["amd-radeon-pro-v520","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"over",null],["amd-radeon-pro-v520","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"over",null],["amd-radeon-pro-v520","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"over",null],["amd-radeon-pro-v520","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["amd-radeon-pro-v520","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["amd-radeon-pro-v520","ministral-3-14b-instruct-2512","rocm","no","Q4_K_M",8192,10.29,null,null,null,null,null],["amd-radeon-pro-v520","ministral-3-14b-reasoning-2512","rocm","no","Q4_K_M",8192,10.29,null,null,null,null,null],["amd-radeon-pro-v520","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-pro-v520","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-pro-v520","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","mistral-small-3-2-24b-instruct-2506","rocm","no","Q2_K",8192,11.09,null,null,null,null,null],["amd-radeon-pro-v520","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["amd-radeon-pro-v520","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-pro-v520","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","no","Q4_K_M",8192,23.26,null,null,null,null,null],["amd-radeon-pro-v520","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-cascade-2-30b-a3b","rocm","no","IQ2_M",8192,19.07,null,null,null,null,null],["amd-radeon-pro-v520","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nemotron-terminal-32b","rocm","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["amd-radeon-pro-v520","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","north-mini-code-1-0","rocm","no","IQ2_XXS",8192,10.7,null,null,null,null,null],["amd-radeon-pro-v520","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","no","Q2_K",8192,18.88,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","no","IQ2_M",8192,19.07,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","no","IQ4_XS",8192,19.09,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","no","IQ2_M",8192,18.88,null,null,null,null,null],["amd-radeon-pro-v520","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-1-32b-instruct","rocm","no","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-1-32b-instruct-dpo","rocm","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-1-32b-think","rocm","no","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-1125-32b","rocm","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-32b-think","rocm","no","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-32b-think-dpo","rocm","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-32b-think-sft","rocm","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["amd-radeon-pro-v520","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","optimind-sft","rocm","no","IQ2_M",8192,13.14,null,null,null,null,null],["amd-radeon-pro-v520","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,null,null],["amd-radeon-pro-v520","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen2-5-32b-instruct","rocm","no","Q2_K",8192,15.24,null,null,null,null,null],["amd-radeon-pro-v520","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,null,null],["amd-radeon-pro-v520","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen2-5-coder-32b-instruct","rocm","no","Q2_K",8192,15.24,null,null,null,null,null],["amd-radeon-pro-v520","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-14b","rocm","no","Q4_K_M",8192,11.03,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-30b-a3b","rocm","no","Q4_K_M",8192,20.13,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-30b-a3b-instruct-2507","rocm","no","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-32b","rocm","no","Q4_K_M",8192,22.37,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-5-27b","rocm","no","Q3_K_M",8192,15.35,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-35b-a3b","rocm","no","Q3_K_M",8192,17.55,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-5-35b-a3b-base","rocm","no","IQ2_XXS",8192,10.92,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-6-27b","rocm","no","Q3_K_M",8192,15.43,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-6-35b-a3b","rocm","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-coder-30b-a3b-instruct","rocm","no","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-coder-next-base","rocm","no","IQ2_XXS",8192,22.32,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"over",null],["amd-radeon-pro-v520","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-vl-30b-a3b-instruct","rocm","no","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-vl-32b-instruct","rocm","no","Q2_K",8192,15.27,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-vl-32b-thinking","rocm","no","Q2_K",8192,15.27,null,null,null,null,null],["amd-radeon-pro-v520","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","qwq-32b","rocm","no","Q4_K_M",8192,22.45,null,null,null,null,null],["amd-radeon-pro-v520","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","sera-32b","rocm","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["amd-radeon-pro-v520","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["amd-radeon-pro-v520","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["amd-radeon-pro-v520","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["amd-radeon-pro-v520","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["amd-radeon-pro-v520","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["amd-radeon-pro-v520","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","translategemma-27b-it","rocm","no","Q2_K",8192,14.43,null,null,null,null,null],["amd-radeon-pro-v520","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["amd-radeon-pro-v520","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["amd-radeon-pro-v520","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["amd-radeon-pro-v520","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ui-mate-27b","rocm","no","IQ2_XXS",8192,11.21,null,null,null,null,null],["amd-radeon-pro-v520","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ui-mate-democua-27b","rocm","no","Q2_K",8192,12.74,null,null,null,null,null],["amd-radeon-pro-v520","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ui-venus-1-5-30b-a3b","rocm","no","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-pro-v520","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","webworld-32b","rocm","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["amd-radeon-pro-v520","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-v520","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-pro-w7800-32gb","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7800-32gb","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-32gb","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-pro-w7800-48gb","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7800-48gb","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7800-48gb","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-pro-w7800-48gb","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7800-48gb","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7800-48gb","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","aescode-32b","rocm","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","aescode-8b","rocm","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","agentcpm-explore","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ai21-jamba-reasoning-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ai21-jamba2-3b","rocm","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ai21-jamba2-mini","rocm","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","apertus-v1-1-1-5b","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","apertus-v1-1-1-5b-instruct","rocm","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","apertus-v1-1-4b","rocm","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","apriel-1-6-15b-thinker","rocm","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","aprielguard","rocm","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","armorocr","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","astabrief-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","autoglm-phone-9b","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","autoglm-phone-9b-multilingual","rocm","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7900","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-pro-w7900","bielik-11b-v3-0-instruct","rocm","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","bielik-minitron-7b-v3-0-instruct","rocm","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","bitcpm-cann-3b-unquantized","rocm","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","caprl-qwen3vl-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","caprl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,null,null],["amd-radeon-pro-w7900","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["amd-radeon-pro-w7900","contextpilot-14b","rocm","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","contextpilot-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","contextpilot-e4b","rocm","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","cosmos-reason2-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","cosmos-reason2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","d1-3b","rocm","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,null,null],["amd-radeon-pro-w7900","deepseek-r1-0528-qwen3-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1-distill-llama-70b","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1-distill-llama-8b","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1-distill-qwen-14b","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1-distill-qwen-32b","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-r1-distill-qwen-7b","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,null,null],["amd-radeon-pro-w7900","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,null,null],["amd-radeon-pro-w7900","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,null,null],["amd-radeon-pro-w7900","devstral-2-123b-instruct-2512","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","devstral-small-2-24b-instruct-2512","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","eurollm-22b-2512","rocm","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","eurollm-22b-instruct-2512","rocm","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","eurollm-9b-instruct-2512","rocm","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","euromoe-2-6b-a0-6b-instruct-2512","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","exaone-4-5-33b","rocm","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","fara-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","fara1-5-27b","rocm","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","fara1-5-4b","rocm","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","fara1-5-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","frogboss-32b-2510","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","frogmini-14b-2510","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","frognano-4b-2609","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","functiongemma-270m-it","rocm","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gelab-zero-4b-preview","rocm","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-2-27b-it","rocm","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-2-9b-it","rocm","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-3-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-3-1b-it","rocm","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-3-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-3-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-12b","rocm","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-12b-it","rocm","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-26b-a4b","rocm","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-26b-a4b-it","rocm","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-31b","rocm","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-31b-it","rocm","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-e2b","rocm","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-e2b-it","rocm","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-e4b","rocm","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","gemma-4-e4b-it","rocm","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7900","glm-4-5-air","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-5-air-reap-82b-a12b","rocm","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,null,null],["amd-radeon-pro-w7900","glm-4-6v","rocm","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-6v-flash","rocm","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,null,null],["amd-radeon-pro-w7900","glm-4-7-flash","rocm","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-7-flash-reap-23b-a3b","rocm","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,null,null],["amd-radeon-pro-w7900","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["amd-radeon-pro-w7900","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,null,null],["amd-radeon-pro-w7900","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["amd-radeon-pro-w7900","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7900","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-pro-w7900","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,null,null],["amd-radeon-pro-w7900","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["amd-radeon-pro-w7900","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,null,null],["amd-radeon-pro-w7900","gpt-oss-20b","rocm","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-3-3-8b-instruct","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-0-1b","rocm","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-0-350m","rocm","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-0-h-1b","rocm","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-0-h-350m","rocm","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-1-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-1-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-1-8b","rocm","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-2-30b","rocm","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-2-3b","rocm","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-4-2-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-guardian-3-2-8b-factuality-detection","rocm","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-guardian-4-0-3b-toxicity-ja","rocm","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-guardian-4-1-8b","rocm","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","granite-vision-4-1-4b","rocm","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","harc-llama-3-1-8b-instruct","rocm","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","harc-qwen2-5-7b-instruct","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","hermes-4-3-36b","rocm","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","hipo-1-7b","rocm","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo-3-1-0-8b","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo-3-1-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo-3-1-4b","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo-3-1-9b","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7900","holo2-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo2-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo2-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo3-35b-a3b","rocm","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo4-27b","rocm","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holo4-35b-a3b","rocm","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","holotron4-30b-a3b","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","hunyuanocr","rocm","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["amd-radeon-pro-w7900","intellect-3","rocm","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-llama3-8b-baseline","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-llama3-8b-multiview","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-4b-baseline","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-4b-multiview","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-8b-baseline","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intent-aware-lfqa-qwen3-8b-multiview","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["amd-radeon-pro-w7900","ising-calibration-1-35b-a3b","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ising-calibration-1-5-31b-bf16","rocm","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","januscoder-14b","rocm","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","januscoder-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","januscoderv-7b","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,null,null],["amd-radeon-pro-w7900","kanana-2-3b-base","rocm","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kanana-2-3b-instruct","rocm","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kat-coder-v2-5-dev","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kat-dev-72b-exp","rocm","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,null,null],["amd-radeon-pro-w7900","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["amd-radeon-pro-w7900","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,null,null],["amd-radeon-pro-w7900","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,null,null],["amd-radeon-pro-w7900","kimi-linear-48b-a3b-base","rocm","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kimi-linear-48b-a3b-instruct","rocm","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","kimi-linear-reap-35b-a3b-instruct","rocm","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,null,null],["amd-radeon-pro-w7900","laguna-xs-2-1","rocm","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-2-6b-exp","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-2-6b-longevity","rocm","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-2-6b-transcript","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-24b-a2b","rocm","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-1-2b-base","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-1-2b-instruct","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-1-2b-jp","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-1-2b-jp-202606","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-1-2b-thinking","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-2-6b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-2-6b-base","rocm","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-230m","rocm","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-24b-a2b","rocm","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-350m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-8b-a1b","rocm","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-encoder-350m-diffusion","rocm","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-vl-1-6b","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-vl-1-6b-extract","rocm","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-vl-3b","rocm","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-vl-450m","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-5-vl-450m-extract","rocm","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-8b-a1b","rocm","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","lfm2-vl-3b","rocm","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,null,null],["amd-radeon-pro-w7900","llama-3-1-70b-instruct","rocm","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","llama-3-1-8b-instruct","rocm","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","llama-3-2-1b-instruct","rocm","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","llama-3-2-3b-instruct","rocm","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","llama-3-3-70b-instruct","rocm","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","llama-4-scout-17b-16e-instruct","rocm","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mathform-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","medgemma-1-5-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-1-12b-a2-5b-thinking","rocm","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-12b-a2-5b-base","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-12b-a2-5b-instruct","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-12b-a2-5b-instruct-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-12b-a2-5b-thinking","rocm","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mellum2-12b-a2-5b-thinking-sft","rocm","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mimo-embodied-7b","rocm","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-6-distill-qwen-9b","rocm","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,null,null],["amd-radeon-pro-w7900","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,null,null],["amd-radeon-pro-w7900","minicpm-o-4-5","rocm","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm-v-4-6","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm-v-4-6-thinking","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm-v-4-7-1b","rocm","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm-v-4-7-35b-a3b","rocm","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm5-1b","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm5-1b-base","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm5-1b-sft","rocm","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm5-2b","rocm","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minicpm5-2b-base","rocm","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7900","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7900","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,null,null],["amd-radeon-pro-w7900","minimax-m2-5-reap-139b-a10b","rocm","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["amd-radeon-pro-w7900","ministral-3-14b-instruct-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ministral-3-14b-reasoning-2512","rocm","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ministral-3-3b-instruct-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ministral-3-3b-reasoning-2512","rocm","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ministral-3-8b-instruct-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ministral-3-8b-reasoning-2512","rocm","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mistral-7b-instruct-v0-2","rocm","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,null,null],["amd-radeon-pro-w7900","mistral-medium-3-5-128b","rocm","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mistral-nemo-instruct-2407","rocm","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mistral-small-3-2-24b-instruct-2506","rocm","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","mistral-small-4-119b-2603","rocm","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","muse-glimmer-30b","rocm","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,null,null],["amd-radeon-pro-w7900","nemotron-3-content-safety","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-cascade-14b-thinking","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-cascade-2-30b-a3b","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-cascade-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-cascade-8b-thinking","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-orchestrator-8b","rocm","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-terminal-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-terminal-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nemotron-terminal-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","north-mini-code-1-0","rocm","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nouscoder-14b","rocm","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,null,null],["amd-radeon-pro-w7900","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-nano-4b-bf16","rocm","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","nvidia-nemotron-nano-9b-v2","rocm","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1-32b-instruct","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1-32b-instruct-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1-7b-rl-zero-math","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-1125-32b","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-32b-think","rocm","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-32b-think-dpo","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-32b-think-sft","rocm","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-instruct","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-instruct-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-instruct-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-rl-zero-code","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-rl-zero-general","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-rl-zero-if","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-rl-zero-math","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-rl-zero-mix","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-think","rocm","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-think-dpo","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmo-3-7b-think-sft","rocm","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","olmocr-2-7b-1025","rocm","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","optimind-sft","rocm","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","phi-3-5-mini-instruct","rocm","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","phi-4","rocm","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","phi-4-mini-instruct","rocm","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen-agentworld-35b-a3b","rocm","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-14b-instruct","rocm","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-3b-instruct","rocm","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-72b-instruct","rocm","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-coder-32b-instruct","rocm","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-coder-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-vl-7b-instruct","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen2-5-vl-7b-surg-cholect50","rocm","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-0-6b","rocm","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-1-7b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-14b","rocm","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-30b-a3b","rocm","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-30b-a3b-instruct-2507","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-32b","rocm","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-4b","rocm","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-4b-instruct-2507","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-0-8b","rocm","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-0-8b-base","rocm","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-122b-a10b","rocm","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-27b","rocm","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-2b","rocm","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-2b-base","rocm","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-35b-a3b","rocm","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-35b-a3b-base","rocm","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-5-4b","rocm","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-4b-base","rocm","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-9b","rocm","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-5-9b-base","rocm","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-6-27b","rocm","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-6-35b-a3b","rocm","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-pro-w7900","qwen3-8-27b","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-8-3-6-27b-blend","rocm","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-8b","rocm","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-coder-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-coder-next","rocm","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-coder-next-base","rocm","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-coder-reap-25b-a3b","rocm","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-nemotron-14b-brrm","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-nemotron-8b-brrm","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-next-80b-a3b-instruct","rocm","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,null,null],["amd-radeon-pro-w7900","qwen3-vl-2b-instruct","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-2b-thinking","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-30b-a3b-instruct","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-32b-instruct","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-32b-thinking","rocm","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-4b-instruct","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-4b-thinking","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-8b-instruct","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwen3-vl-8b-thinking","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","qwq-32b","rocm","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","riva-translate-4b-instruct-v1-1","rocm","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","rlvr-8b-0926","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","rnj-1-instruct","rocm","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","sera-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","singguard-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","smollm3-3b","rocm","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","smollm3-3b-gsm8k-sft","rocm","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","solar-open-100b","rocm","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","spatial-ssrl-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","spatial-ssrl-qwen3vl-4b","rocm","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","step-3-5-flash","rocm","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","step-3-5-flash-reap-121b-a11b","rocm","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","step-3-5-flash-reap-149b-a11b","rocm","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["amd-radeon-pro-w7900","step3-vl-10b-base","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","tiny-aya-earth","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","tiny-aya-fire","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","tiny-aya-global","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","tiny-aya-water","rocm","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","translategemma-12b-it","rocm","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","translategemma-27b-it","rocm","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","translategemma-4b-it","rocm","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7900","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["amd-radeon-pro-w7900","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["amd-radeon-pro-w7900","trinity-mini","rocm","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-mini-base","rocm","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-mini-base-pre-anneal","rocm","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-nano-base","rocm","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-nano-base-pre-anneal","rocm","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","trinity-nano-preview","rocm","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-mate-27b","rocm","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-mate-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-mate-democua-27b","rocm","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-venus-1-5-2b","rocm","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-venus-1-5-30b-a3b","rocm","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-venus-1-5-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","ui-venus-2-9b","rocm","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","userrepgen-4b","rocm","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","webworld-14b","rocm","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","webworld-32b","rocm","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","webworld-8b","rocm","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","x-reasoner-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","youtu-llm-2b","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","youtu-llm-2b-base","rocm","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","youtu-vl-4b-instruct","rocm","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","zwz-2b","rocm","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","zwz-4b","rocm","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","zwz-7b","rocm","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["amd-radeon-pro-w7900","zwz-8b","rocm","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["amd-radeon-rx-7700-xt","aescode-32b","rocm","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["amd-radeon-rx-7700-xt","aescode-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","agentcpm-explore","rocm","fits","Q6_K",8192,5.74,41472,false,null,null,null],["amd-radeon-rx-7700-xt","ai21-jamba-reasoning-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7700-xt","ai21-jamba2-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7700-xt","ai21-jamba2-mini","rocm","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["amd-radeon-rx-7700-xt","apertus-v1-1-1-5b","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7700-xt","apertus-v1-1-1-5b-instruct","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7700-xt","apertus-v1-1-4b","rocm","fits","Q6_K",4096,4.42,4096,false,null,null,null],["amd-radeon-rx-7700-xt","apriel-1-6-15b-thinker","rocm","fits","IQ4_XS",8192,10.25,9984,false,null,null,null],["amd-radeon-rx-7700-xt","aprielguard","rocm","fits","Q6_K",8192,7.87,36096,false,null,null,null],["amd-radeon-rx-7700-xt","armorocr","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","astabrief-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","autoglm-phone-9b","rocm","fits","Q6_K",8192,9.25,40704,false,null,null,null],["amd-radeon-rx-7700-xt","autoglm-phone-9b-multilingual","rocm","fits","Q6_K",8192,9.25,40704,false,null,null,null],["amd-radeon-rx-7700-xt","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"8",null],["amd-radeon-rx-7700-xt","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-rx-7700-xt","bielik-11b-v3-0-instruct","rocm","fits","Q5_K_M",8192,10.59,8192,false,null,null,null],["amd-radeon-rx-7700-xt","bielik-minitron-7b-v3-0-instruct","rocm","fits","Q8_0",8192,10.25,10496,false,null,null,null],["amd-radeon-rx-7700-xt","bitcpm-cann-3b-unquantized","rocm","fits","Q6_K",8192,4.29,32768,false,null,null,null],["amd-radeon-rx-7700-xt","caprl-qwen3vl-2b","rocm","fits","F16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","caprl-qwen3vl-4b","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-rx-7700-xt","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","contextpilot-14b","rocm","fits","IQ4_XS",8192,10.35,9728,false,null,null,null],["amd-radeon-rx-7700-xt","contextpilot-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","contextpilot-e4b","rocm","fits","Q8_0",8192,6.65,131072,false,null,null,null],["amd-radeon-rx-7700-xt","cosmos-reason2-32b","rocm","tight","IQ2_M",8192,14.23,null,null,null,null,null],["amd-radeon-rx-7700-xt","cosmos-reason2-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","d1-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7700-xt","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-rx-7700-xt","deepseek-r1-0528-qwen3-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,"4",null],["amd-radeon-rx-7700-xt","deepseek-r1-distill-llama-8b","rocm","fits","Q8_0",8192,10.15,11776,false,null,null,null],["amd-radeon-rx-7700-xt","deepseek-r1-distill-qwen-14b","rocm","fits","Q3_K_M",8192,9.76,12544,false,null,null,null],["amd-radeon-rx-7700-xt","deepseek-r1-distill-qwen-32b","rocm","no","Q2_K",8192,15.24,null,null,null,"2",null],["amd-radeon-rx-7700-xt","deepseek-r1-distill-qwen-7b","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-rx-7700-xt","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-rx-7700-xt","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-rx-7700-xt","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,"6",null],["amd-radeon-rx-7700-xt","devstral-small-2-24b-instruct-2512","rocm","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["amd-radeon-rx-7700-xt","eurollm-22b-2512","rocm","fits","IQ2_M",8192,10.57,8448,false,null,null,null],["amd-radeon-rx-7700-xt","eurollm-22b-instruct-2512","rocm","fits","IQ2_M",8192,10.57,8448,false,null,null,null],["amd-radeon-rx-7700-xt","eurollm-9b-instruct-2512","rocm","fits","Q6_K",8192,9.6,14080,false,null,null,null],["amd-radeon-rx-7700-xt","euromoe-2-6b-a0-6b-instruct-2512","rocm","fits","Q6_K",8192,3.58,32768,false,null,null,null],["amd-radeon-rx-7700-xt","exaone-4-5-33b","rocm","no","IQ4_XS",8192,20.43,null,null,null,"3",null],["amd-radeon-rx-7700-xt","fara-7b","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","fara1-5-27b","rocm","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["amd-radeon-rx-7700-xt","fara1-5-4b","rocm","fits","BF16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","fara1-5-9b","rocm","fits","Q8_0",8192,10.27,18432,false,null,null,null],["amd-radeon-rx-7700-xt","frogboss-32b-2510","rocm","tight","IQ2_M",8192,14.23,null,null,null,null,null],["amd-radeon-rx-7700-xt","frogmini-14b-2510","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","frognano-4b-2609","rocm","fits","BF16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","functiongemma-270m-it","rocm","fits","BF16",8192,2.14,32768,false,null,null,null],["amd-radeon-rx-7700-xt","gelab-zero-4b-preview","rocm","fits","BF16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-2-27b-it","rocm","tight","IQ3_XXS",8192,15.11,null,null,null,null,null],["amd-radeon-rx-7700-xt","gemma-2-9b-it","rocm","fits","IQ4_XS",8192,9.39,8192,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-3-12b-it","rocm","fits","Q4_0",8192,10.33,12544,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-3-1b-it","rocm","fits","BF16",8192,3.6,32768,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-3-27b-it","rocm","tight","Q2_K",8192,14.43,null,null,null,null,null],["amd-radeon-rx-7700-xt","gemma-3-4b-it","rocm","fits","BF16",8192,9.86,42496,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-12b","rocm","tight","Q8_0",8192,15.57,null,null,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-12b-it","rocm","fits","Q4_K_M",8192,10.13,35328,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-26b-a4b","rocm","tight","Q2_K",8192,13,null,null,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-26b-a4b-it","rocm","tight","Q3_K_M",8192,15.39,null,null,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-31b","rocm","no","Q2_K",8192,17.58,null,null,null,"2",null],["amd-radeon-rx-7700-xt","gemma-4-31b-it","rocm","no","Q3_K_M",8192,20.34,null,null,null,"3",null],["amd-radeon-rx-7700-xt","gemma-4-e2b","rocm","fits","Q6_K",8192,3.49,131072,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-e2b-it","rocm","fits","BF16",8192,6.14,131072,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-e4b","rocm","fits","Q8_0",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7700-xt","gemma-4-e4b-it","rocm","fits","Q8_0",8192,6.86,131072,false,null,null,null],["amd-radeon-rx-7700-xt","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,"6",null],["amd-radeon-rx-7700-xt","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,"4",null],["amd-radeon-rx-7700-xt","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,"6",null],["amd-radeon-rx-7700-xt","glm-4-6v-flash","rocm","fits","Q6_K",8192,9.25,40704,false,null,null,null],["amd-radeon-rx-7700-xt","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-4-7-flash","rocm","tight","Q2_K",8192,12.77,null,null,null,null,null],["amd-radeon-rx-7700-xt","glm-4-7-flash-reap-23b-a3b","rocm","fits","Q2_K",8192,10.25,14848,false,null,null,null],["amd-radeon-rx-7700-xt","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-rx-7700-xt","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,"8",null],["amd-radeon-rx-7700-xt","gpt-oss-20b","rocm","tight","Q8_0",8192,12.9,null,null,null,null,null],["amd-radeon-rx-7700-xt","granite-3-3-8b-instruct","rocm","fits","Q6_K",8192,9.17,17152,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-0-1b","rocm","fits","BF16",8192,5.14,74752,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-0-350m","rocm","fits","BF16",8192,2.2,32768,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-0-h-1b","rocm","fits","BF16",8192,4.44,131072,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-0-h-350m","rocm","fits","BF16",8192,2.07,32768,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-1-30b","rocm","tight","Q2_K",8192,13.89,null,null,null,null,null],["amd-radeon-rx-7700-xt","granite-4-1-3b","rocm","fits","BF16",8192,8.61,32512,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-1-8b","rocm","fits","Q6_K",8192,9.34,15872,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-2-30b","rocm","tight","Q2_K",8192,13.89,null,null,null,null,null],["amd-radeon-rx-7700-xt","granite-4-2-3b","rocm","fits","BF16",8192,8.61,32512,false,null,null,null],["amd-radeon-rx-7700-xt","granite-4-2-8b","rocm","fits","Q6_K",8192,9.34,15872,false,null,null,null],["amd-radeon-rx-7700-xt","granite-guardian-3-2-8b-factuality-detection","rocm","fits","Q6_K",8192,9.17,17152,false,null,null,null],["amd-radeon-rx-7700-xt","granite-guardian-4-0-3b-toxicity-ja","rocm","fits","Q6_K",8192,4.67,80384,false,null,null,null],["amd-radeon-rx-7700-xt","granite-guardian-4-1-8b","rocm","fits","Q6_K",8192,9.34,15872,false,null,null,null],["amd-radeon-rx-7700-xt","granite-vision-4-1-4b","rocm","fits","BF16",8192,8.61,32512,false,null,null,null],["amd-radeon-rx-7700-xt","harc-llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,25344,false,null,null,null],["amd-radeon-rx-7700-xt","harc-qwen2-5-7b-instruct","rocm","fits","Q6_K",8192,7.47,32768,false,null,null,null],["amd-radeon-rx-7700-xt","hermes-4-3-36b","rocm","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["amd-radeon-rx-7700-xt","hipo-1-7b","rocm","fits","Q6_K",8192,3.63,40960,false,null,null,null],["amd-radeon-rx-7700-xt","holo-3-1-0-8b","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7700-xt","holo-3-1-35b-a3b","rocm","tight","Q2_K",8192,14.45,null,null,null,null,null],["amd-radeon-rx-7700-xt","holo-3-1-4b","rocm","fits","F16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","holo-3-1-9b","rocm","fits","Q8_0",8192,10.25,18944,false,null,null,null],["amd-radeon-rx-7700-xt","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"8",null],["amd-radeon-rx-7700-xt","holo2-30b-a3b","rocm","tight","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-rx-7700-xt","holo2-4b","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","holo2-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","holo3-35b-a3b","rocm","tight","Q2_K",8192,14.45,null,null,null,null,null],["amd-radeon-rx-7700-xt","holo4-27b","rocm","fits","IQ2_XXS",8192,10.5,9984,false,null,null,null],["amd-radeon-rx-7700-xt","holo4-35b-a3b","rocm","tight","Q2_K",8192,14.96,null,null,null,null,null],["amd-radeon-rx-7700-xt","holotron4-30b-a3b","rocm","no","IQ2_M",8192,18.88,null,null,null,"3",null],["amd-radeon-rx-7700-xt","hunyuanocr","rocm","fits","F16",8192,3.13,32768,false,null,null,null],["amd-radeon-rx-7700-xt","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,"5",null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-llama3-8b-baseline","rocm","fits","Q8_0",8192,10.15,11776,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.15,11776,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.15,11776,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-llama3-8b-multiview","rocm","fits","Q8_0",8192,10.15,11776,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-4b-baseline","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-4b-multiview","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-8b-baseline","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intent-aware-lfqa-qwen3-8b-multiview","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["amd-radeon-rx-7700-xt","ising-calibration-1-35b-a3b","rocm","tight","IQ3_XXS",8192,15.07,null,null,null,null,null],["amd-radeon-rx-7700-xt","ising-calibration-1-5-31b-bf16","rocm","tight","IQ2_XXS",8192,16.51,null,null,null,null,null],["amd-radeon-rx-7700-xt","januscoder-14b","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","januscoder-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","januscoderv-7b","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["amd-radeon-rx-7700-xt","kanana-2-3b-base","rocm","fits","Q6_K",8192,4.89,32768,false,null,null,null],["amd-radeon-rx-7700-xt","kanana-2-3b-instruct","rocm","fits","F16",8192,8.57,23808,false,null,null,null],["amd-radeon-rx-7700-xt","kat-coder-v2-5-dev","rocm","tight","Q2_K",8192,14.13,null,null,null,null,null],["amd-radeon-rx-7700-xt","kat-dev-72b-exp","rocm","no","IQ2_XXS",8192,28.54,null,null,null,"4",null],["amd-radeon-rx-7700-xt","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-rx-7700-xt","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-rx-7700-xt","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-rx-7700-xt","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-rx-7700-xt","kimi-linear-48b-a3b-base","rocm","tight","IQ2_XXS",8192,14.24,null,null,null,null,null],["amd-radeon-rx-7700-xt","kimi-linear-48b-a3b-instruct","rocm","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["amd-radeon-rx-7700-xt","kimi-linear-reap-35b-a3b-instruct","rocm","tight","IQ3_XXS",8192,14.77,null,null,null,null,null],["amd-radeon-rx-7700-xt","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","laguna-xs-2-1","rocm","tight","Q2_K",8192,13.77,null,null,null,null,null],["amd-radeon-rx-7700-xt","lfm2-2-6b-exp","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-2-6b-longevity","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-2-6b-transcript","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-24b-a2b","rocm","tight","Q4_0",8192,14.65,null,null,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-1-2b-base","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-1-2b-instruct","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-1-2b-jp","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-1-2b-jp-202606","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-1-2b-thinking","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-2-6b","rocm","fits","BF16",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-2-6b-base","rocm","fits","Q6_K",8192,3.58,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-230m","rocm","fits","BF16",8192,1.83,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-24b-a2b","rocm","tight","Q4_0",8192,14.75,null,null,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-350m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-8b-a1b","rocm","fits","Q8_0",8192,10.2,37888,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-encoder-350m-diffusion","rocm","fits","Q6_K",8192,1.66,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-vl-1-6b","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-vl-1-6b-extract","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-vl-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-vl-450m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-5-vl-450m-extract","rocm","fits","F16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-8b-a1b","rocm","fits","Q8_0",8192,10.07,47360,false,null,null,null],["amd-radeon-rx-7700-xt","lfm2-vl-3b","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7700-xt","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-rx-7700-xt","llama-3-1-70b-instruct","rocm","no","IQ2_XXS",8192,22.29,null,null,null,"3",null],["amd-radeon-rx-7700-xt","llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,25344,false,null,null,null],["amd-radeon-rx-7700-xt","llama-3-2-1b-instruct","rocm","fits","BF16",8192,3.97,131072,false,null,null,null],["amd-radeon-rx-7700-xt","llama-3-2-3b-instruct","rocm","fits","BF16",8192,8.5,26624,false,null,null,null],["amd-radeon-rx-7700-xt","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,"4",null],["amd-radeon-rx-7700-xt","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,"5",null],["amd-radeon-rx-7700-xt","mathform-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","medgemma-1-5-4b-it","rocm","fits","BF16",8192,9.86,42496,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-1-12b-a2-5b-thinking","rocm","fits","Q4_K_M",8192,9.38,85504,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-12b-a2-5b-base","rocm","fits","Q5_K_M",8192,10.47,17408,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-12b-a2-5b-instruct","rocm","fits","Q5_K_M",8192,10.55,12800,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-12b-a2-5b-instruct-sft","rocm","fits","Q5_K_M",8192,10.47,17408,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-12b-a2-5b-thinking","rocm","fits","Q5_K_M",8192,10.55,12800,false,null,null,null],["amd-radeon-rx-7700-xt","mellum2-12b-a2-5b-thinking-sft","rocm","fits","Q5_K_M",8192,10.47,17408,false,null,null,null],["amd-radeon-rx-7700-xt","mimo-embodied-7b","rocm","fits","Q6_K",8192,8.14,25088,false,null,null,null],["amd-radeon-rx-7700-xt","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mimo-v2-6-distill-qwen-9b","rocm","fits","Q8_0",8192,10.27,18432,false,null,null,null],["amd-radeon-rx-7700-xt","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"over",null],["amd-radeon-rx-7700-xt","minicpm-o-4-5","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm-v-4-6","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm-v-4-6-thinking","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm-v-4-7-1b","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm-v-4-7-35b-a3b","rocm","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["amd-radeon-rx-7700-xt","minicpm5-1b","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm5-1b-base","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm5-1b-sft","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm5-2b","rocm","fits","BF16",8192,6.04,111872,false,null,null,null],["amd-radeon-rx-7700-xt","minicpm5-2b-base","rocm","fits","Q6_K",8192,3.43,170752,false,null,null,null],["amd-radeon-rx-7700-xt","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,"5",null],["amd-radeon-rx-7700-xt","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,"8",null],["amd-radeon-rx-7700-xt","ministral-3-14b-instruct-2512","rocm","fits","Q4_K_M",8192,10.29,9984,false,null,null,null],["amd-radeon-rx-7700-xt","ministral-3-14b-reasoning-2512","rocm","fits","Q4_K_M",8192,10.29,9984,false,null,null,null],["amd-radeon-rx-7700-xt","ministral-3-3b-instruct-2512","rocm","fits","BF16",8192,8.86,24576,false,null,null,null],["amd-radeon-rx-7700-xt","ministral-3-3b-reasoning-2512","rocm","fits","BF16",8192,8.86,24576,false,null,null,null],["amd-radeon-rx-7700-xt","ministral-3-8b-instruct-2512","rocm","fits","Q5_K_M",8192,7.97,27136,false,null,null,null],["amd-radeon-rx-7700-xt","ministral-3-8b-reasoning-2512","rocm","fits","Q5_K_M",8192,7.97,27136,false,null,null,null],["amd-radeon-rx-7700-xt","mistral-7b-instruct-v0-2","rocm","fits","Q6_K",8192,8.05,27904,false,null,null,null],["amd-radeon-rx-7700-xt","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-rx-7700-xt","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,"6",null],["amd-radeon-rx-7700-xt","mistral-nemo-instruct-2407","rocm","fits","Q4_K_M",8192,9.55,14592,false,null,null,null],["amd-radeon-rx-7700-xt","mistral-small-3-2-24b-instruct-2506","rocm","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["amd-radeon-rx-7700-xt","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,"5",null],["amd-radeon-rx-7700-xt","muse-glimmer-30b","rocm","fits","IQ2_XXS",8192,10.17,37120,false,null,null,null],["amd-radeon-rx-7700-xt","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-rx-7700-xt","nemotron-3-content-safety","rocm","fits","Q6_K",8192,5.37,131072,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nemotron-cascade-14b-thinking","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-cascade-2-30b-a3b","rocm","no","IQ2_M",8192,19.07,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nemotron-cascade-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-cascade-8b-thinking","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-orchestrator-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-terminal-14b","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","nemotron-terminal-32b","rocm","tight","IQ2_M",8192,14.23,null,null,null,null,null],["amd-radeon-rx-7700-xt","nemotron-terminal-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","north-mini-code-1-0","rocm","tight","IQ3_XXS",8192,15.09,null,null,null,null,null],["amd-radeon-rx-7700-xt","nouscoder-14b","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","no","Q2_K",8192,18.88,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","no","IQ2_M",8192,19.07,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,"8",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-nano-4b-bf16","rocm","fits","BF16",8192,8.73,112896,false,null,null,null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,"6",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,"6",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","no","IQ2_M",8192,18.88,null,null,null,"3",null],["amd-radeon-rx-7700-xt","nvidia-nemotron-nano-9b-v2","rocm","fits","Q6_K",8192,10.32,25088,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1-32b-instruct","rocm","tight","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1-32b-instruct-dpo","rocm","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1-32b-think","rocm","tight","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1-7b-rl-zero-code","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1-7b-rl-zero-math","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-1125-32b","rocm","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-32b-think","rocm","tight","Q2_K",8192,15,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-32b-think-dpo","rocm","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-32b-think-sft","rocm","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-instruct","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-instruct-dpo","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-instruct-sft","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-rl-zero-code","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-rl-zero-general","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-rl-zero-if","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-rl-zero-math","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-rl-zero-mix","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-think","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-think-dpo","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmo-3-7b-think-sft","rocm","fits","Q5_K_M",8192,10.33,8704,false,null,null,null],["amd-radeon-rx-7700-xt","olmocr-2-7b-1025","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","optimind-sft","rocm","tight","Q4_0",8192,13.22,null,null,null,null,null],["amd-radeon-rx-7700-xt","phi-3-5-mini-instruct","rocm","fits","Q8_0",8192,8.32,14080,false,null,null,null],["amd-radeon-rx-7700-xt","phi-4","rocm","fits","Q3_K_M",8192,9.75,12288,false,null,null,null],["amd-radeon-rx-7700-xt","phi-4-mini-instruct","rocm","fits","BF16",8192,9.99,12800,false,null,null,null],["amd-radeon-rx-7700-xt","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,"5",null],["amd-radeon-rx-7700-xt","qwen2-5-14b-instruct","rocm","fits","Q3_K_M",8192,9.76,12544,false,null,null,null],["amd-radeon-rx-7700-xt","qwen2-5-32b-instruct","rocm","no","Q2_K",8192,15.24,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen2-5-3b-instruct","rocm","fits","Q8_0",8192,4.83,32768,false,null,null,null],["amd-radeon-rx-7700-xt","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,"4",null],["amd-radeon-rx-7700-xt","qwen2-5-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7700-xt","qwen2-5-coder-32b-instruct","rocm","no","Q2_K",8192,15.24,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen2-5-coder-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7700-xt","qwen2-5-vl-7b-instruct","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","qwen2-5-vl-7b-surg-cholect50","rocm","fits","Q8_0",8192,9.15,33536,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-0-6b","rocm","fits","BF16",8192,3.41,40960,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-1-7b","rocm","fits","BF16",8192,5.62,40960,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-14b","rocm","tight","Q6_K",8192,13.89,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["amd-radeon-rx-7700-xt","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","qwen3-30b-a3b","rocm","no","Q4_K_M",8192,20.13,null,null,null,"3",null],["amd-radeon-rx-7700-xt","qwen3-30b-a3b-instruct-2507","rocm","tight","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-32b","rocm","no","Q4_K_M",8192,22.37,null,null,null,"3",null],["amd-radeon-rx-7700-xt","qwen3-4b","rocm","fits","Q8_0",8192,6.7,34816,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-4b-instruct-2507","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-0-8b","rocm","fits","BF16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-0-8b-base","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["amd-radeon-rx-7700-xt","qwen3-5-27b","rocm","tight","Q3_K_M",8192,15.35,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-2b","rocm","fits","BF16",8192,5.38,262144,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-2b-base","rocm","fits","Q6_K",8192,3.21,262144,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-35b-a3b","rocm","no","Q3_K_M",8192,17.55,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen3-5-35b-a3b-base","rocm","tight","IQ3_XXS",8192,14.98,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["amd-radeon-rx-7700-xt","qwen3-5-4b","rocm","fits","BF16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-4b-base","rocm","fits","F16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-9b","rocm","fits","Q8_0",8192,10.25,18944,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-5-9b-base","rocm","fits","Q8_0",8192,10.25,18944,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-6-27b","rocm","no","Q3_K_M",8192,15.43,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen3-6-35b-a3b","rocm","tight","Q2_K",8192,14.12,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-rx-7700-xt","qwen3-8-27b","rocm","fits","IQ2_XXS",8192,10.58,8704,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-8-3-6-27b-blend","rocm","fits","IQ2_XXS",8192,10.58,8704,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-coder-30b-a3b-instruct","rocm","tight","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"over",null],["amd-radeon-rx-7700-xt","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,"4",null],["amd-radeon-rx-7700-xt","qwen3-coder-next-base","rocm","no","IQ2_XXS",8192,22.32,null,null,null,"3",null],["amd-radeon-rx-7700-xt","qwen3-coder-reap-25b-a3b","rocm","fits","IQ2_M",8192,9.92,15360,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"over",null],["amd-radeon-rx-7700-xt","qwen3-nemotron-14b-brrm","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"8",null],["amd-radeon-rx-7700-xt","qwen3-nemotron-8b-brrm","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,"4",null],["amd-radeon-rx-7700-xt","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","qwen3-vl-2b-instruct","rocm","fits","BF16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-2b-thinking","rocm","fits","BF16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-30b-a3b-instruct","rocm","tight","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-32b-instruct","rocm","no","Q2_K",8192,15.27,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen3-vl-32b-thinking","rocm","no","Q2_K",8192,15.27,null,null,null,"2",null],["amd-radeon-rx-7700-xt","qwen3-vl-4b-instruct","rocm","fits","BF16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-4b-thinking","rocm","fits","BF16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-8b-instruct","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwen3-vl-8b-thinking","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","qwq-32b","rocm","no","Q4_K_M",8192,22.45,null,null,null,"3",null],["amd-radeon-rx-7700-xt","riva-translate-4b-instruct-v1-1","rocm","fits","Q6_K",8192,5.97,8192,false,null,null,null],["amd-radeon-rx-7700-xt","rlvr-8b-0926","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","rnj-1-instruct","rocm","fits","Q6_K",8192,9.02,20480,false,null,null,null],["amd-radeon-rx-7700-xt","sera-32b","rocm","tight","IQ2_M",8192,14.23,null,null,null,null,null],["amd-radeon-rx-7700-xt","singguard-2b","rocm","fits","F16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","smollm3-3b","rocm","fits","BF16",8192,7.9,44800,false,null,null,null],["amd-radeon-rx-7700-xt","smollm3-3b-gsm8k-sft","rocm","fits","Q6_K",8192,4.35,65536,false,null,null,null],["amd-radeon-rx-7700-xt","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,"4",null],["amd-radeon-rx-7700-xt","spatial-ssrl-7b","rocm","fits","Q6_K",8192,7.47,62208,false,null,null,null],["amd-radeon-rx-7700-xt","spatial-ssrl-qwen3vl-4b","rocm","fits","F16",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,"6",null],["amd-radeon-rx-7700-xt","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,"4",null],["amd-radeon-rx-7700-xt","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,"5",null],["amd-radeon-rx-7700-xt","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","step3-vl-10b-base","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","tiny-aya-earth","rocm","fits","BF16",8192,8.72,78592,false,null,null,null],["amd-radeon-rx-7700-xt","tiny-aya-fire","rocm","fits","BF16",8192,8.72,78592,false,null,null,null],["amd-radeon-rx-7700-xt","tiny-aya-global","rocm","fits","BF16",8192,8.72,78592,false,null,null,null],["amd-radeon-rx-7700-xt","tiny-aya-water","rocm","fits","BF16",8192,8.72,78592,false,null,null,null],["amd-radeon-rx-7700-xt","translategemma-12b-it","rocm","fits","IQ4_XS",8192,10.03,17152,false,null,null,null],["amd-radeon-rx-7700-xt","translategemma-27b-it","rocm","tight","Q2_K",8192,14.43,null,null,null,null,null],["amd-radeon-rx-7700-xt","translategemma-4b-it","rocm","fits","F16",8192,9.86,42496,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7700-xt","trinity-mini","rocm","fits","IQ2_M",8192,10.1,35840,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-mini-base","rocm","fits","IQ2_M",8192,10.28,25600,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-mini-base-pre-anneal","rocm","fits","IQ2_M",4096,10,4096,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-nano-base","rocm","fits","Q6_K",8192,6.67,131072,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-nano-base-pre-anneal","rocm","fits","Q6_K",4096,6.43,4096,false,null,null,null],["amd-radeon-rx-7700-xt","trinity-nano-preview","rocm","fits","Q8_0",8192,8.08,131072,false,null,null,null],["amd-radeon-rx-7700-xt","ui-mate-27b","rocm","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["amd-radeon-rx-7700-xt","ui-mate-9b","rocm","fits","Q8_0",8192,10.27,18432,false,null,null,null],["amd-radeon-rx-7700-xt","ui-mate-democua-27b","rocm","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["amd-radeon-rx-7700-xt","ui-venus-1-5-2b","rocm","fits","F16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","ui-venus-1-5-30b-a3b","rocm","tight","Q2_K",8192,13.04,null,null,null,null,null],["amd-radeon-rx-7700-xt","ui-venus-1-5-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7700-xt","ui-venus-2-9b","rocm","fits","Q8_0",8192,10.27,18432,false,null,null,null],["amd-radeon-rx-7700-xt","userrepgen-4b","rocm","fits","BF16",8192,10.23,19456,false,null,null,null],["amd-radeon-rx-7700-xt","webworld-14b","rocm","fits","Q4_0",8192,10.58,8448,false,null,null,null],["amd-radeon-rx-7700-xt","webworld-32b","rocm","tight","IQ2_M",8192,14.23,null,null,null,null,null],["amd-radeon-rx-7700-xt","webworld-8b","rocm","fits","Q8_0",8192,10.39,9728,false,null,null,null],["amd-radeon-rx-7700-xt","x-reasoner-7b","rocm","fits","Q6_K",8192,7.47,62208,false,null,null,null],["amd-radeon-rx-7700-xt","youtu-llm-2b","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7700-xt","youtu-llm-2b-base","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7700-xt","youtu-vl-4b-instruct","rocm","fits","Q6_K",8192,5.91,32768,false,null,null,null],["amd-radeon-rx-7700-xt","zwz-2b","rocm","fits","F16",8192,5.62,51712,false,null,null,null],["amd-radeon-rx-7700-xt","zwz-4b","rocm","fits","Q6_K",8192,5.74,41472,false,null,null,null],["amd-radeon-rx-7700-xt","zwz-7b","rocm","fits","Q6_K",8192,7.47,62208,false,null,null,null],["amd-radeon-rx-7700-xt","zwz-8b","rocm","fits","Q6_K",8192,8.59,22016,false,null,null,null],["amd-radeon-rx-7800-xt","aescode-32b","rocm","fits","IQ2_XXS",8192,13.6,12544,false,null,null,null],["amd-radeon-rx-7800-xt","aescode-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","agentcpm-explore","rocm","fits","Q6_K",8192,5.74,69632,false,null,null,null],["amd-radeon-rx-7800-xt","ai21-jamba-reasoning-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7800-xt","ai21-jamba2-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7800-xt","ai21-jamba2-mini","rocm","fits","IQ2_XXS",8192,13.63,70144,false,null,null,null],["amd-radeon-rx-7800-xt","apertus-v1-1-1-5b","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7800-xt","apertus-v1-1-1-5b-instruct","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7800-xt","apertus-v1-1-4b","rocm","fits","Q6_K",4096,4.42,4096,false,null,null,null],["amd-radeon-rx-7800-xt","apriel-1-6-15b-thinker","rocm","fits","Q6_K",8192,13.92,12288,false,null,null,null],["amd-radeon-rx-7800-xt","aprielguard","rocm","fits","Q6_K",8192,7.87,78080,false,null,null,null],["amd-radeon-rx-7800-xt","armorocr","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","astabrief-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7800-xt","autoglm-phone-9b","rocm","fits","Q8_0",8192,10.8,65536,false,null,null,null],["amd-radeon-rx-7800-xt","autoglm-phone-9b-multilingual","rocm","fits","Q6_K",8192,9.25,65536,false,null,null,null],["amd-radeon-rx-7800-xt","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7800-xt","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-rx-7800-xt","bielik-11b-v3-0-instruct","rocm","fits","Q8_0",8192,14.42,9728,false,null,null,null],["amd-radeon-rx-7800-xt","bielik-minitron-7b-v3-0-instruct","rocm","fits","Q8_0",8192,10.25,32768,false,null,null,null],["amd-radeon-rx-7800-xt","bitcpm-cann-3b-unquantized","rocm","fits","Q6_K",8192,4.29,32768,false,null,null,null],["amd-radeon-rx-7800-xt","caprl-qwen3vl-2b","rocm","fits","F16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","caprl-qwen3vl-4b","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-rx-7800-xt","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,"6",null],["amd-radeon-rx-7800-xt","contextpilot-14b","rocm","fits","Q6_K",8192,14.34,10496,false,null,null,null],["amd-radeon-rx-7800-xt","contextpilot-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7800-xt","contextpilot-e4b","rocm","fits","F16",8192,10.89,131072,false,null,null,null],["amd-radeon-rx-7800-xt","cosmos-reason2-32b","rocm","fits","IQ2_M",8192,14.23,9984,false,null,null,null],["amd-radeon-rx-7800-xt","cosmos-reason2-8b","rocm","fits","Q6_K",8192,8.59,50176,false,null,null,null],["amd-radeon-rx-7800-xt","d1-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7800-xt","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-rx-7800-xt","deepseek-r1-0528-qwen3-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,"3",null],["amd-radeon-rx-7800-xt","deepseek-r1-distill-llama-8b","rocm","fits","Q8_0",8192,10.15,43264,false,null,null,null],["amd-radeon-rx-7800-xt","deepseek-r1-distill-qwen-14b","rocm","fits","Q6_K",8192,14.16,11008,false,null,null,null],["amd-radeon-rx-7800-xt","deepseek-r1-distill-qwen-32b","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7800-xt","deepseek-r1-distill-qwen-7b","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-rx-7800-xt","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-rx-7800-xt","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-rx-7800-xt","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,"4",null],["amd-radeon-rx-7800-xt","devstral-small-2-24b-instruct-2512","rocm","fits","IQ4_XS",8192,14.75,8192,false,null,null,null],["amd-radeon-rx-7800-xt","eurollm-22b-2512","rocm","fits","IQ4_XS",8192,14.71,8192,false,null,null,null],["amd-radeon-rx-7800-xt","eurollm-22b-instruct-2512","rocm","fits","IQ4_XS",8192,14.71,8192,false,null,null,null],["amd-radeon-rx-7800-xt","eurollm-9b-instruct-2512","rocm","fits","Q8_0",8192,11.65,26112,false,null,null,null],["amd-radeon-rx-7800-xt","euromoe-2-6b-a0-6b-instruct-2512","rocm","fits","Q6_K",8192,3.58,32768,false,null,null,null],["amd-radeon-rx-7800-xt","exaone-4-5-33b","rocm","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["amd-radeon-rx-7800-xt","fara-7b","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","fara1-5-27b","rocm","fits","IQ3_XXS",8192,14.25,15616,false,null,null,null],["amd-radeon-rx-7800-xt","fara1-5-4b","rocm","fits","BF16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","fara1-5-9b","rocm","fits","Q8_0",8192,10.27,139264,false,null,null,null],["amd-radeon-rx-7800-xt","frogboss-32b-2510","rocm","fits","IQ2_M",8192,14.23,9984,false,null,null,null],["amd-radeon-rx-7800-xt","frogmini-14b-2510","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","frognano-4b-2609","rocm","fits","BF16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","functiongemma-270m-it","rocm","fits","BF16",8192,2.14,32768,false,null,null,null],["amd-radeon-rx-7800-xt","gelab-zero-4b-preview","rocm","fits","BF16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-2-27b-it","rocm","fits","IQ2_M",8192,13.78,8192,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-2-9b-it","rocm","fits","Q6_K",8192,11.96,8192,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-3-12b-it","rocm","fits","Q6_K",8192,13.02,34048,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-3-1b-it","rocm","fits","BF16",8192,3.6,32768,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-3-27b-it","rocm","fits","Q2_K",8192,14.43,12032,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-3-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-12b","rocm","tight","Q8_0",8192,15.57,null,null,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-12b-it","rocm","fits","Q6_K",8192,12.74,119296,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-26b-a4b","rocm","fits","Q2_K",8192,13,87296,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-26b-a4b-it","rocm","fits","IQ3_XXS",8192,14.55,17152,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-31b","rocm","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-31b-it","rocm","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-e2b","rocm","fits","Q6_K",8192,3.49,131072,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-e2b-it","rocm","fits","BF16",8192,6.14,131072,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-e4b","rocm","fits","F16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7800-xt","gemma-4-e4b-it","rocm","fits","BF16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7800-xt","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,"4",null],["amd-radeon-rx-7800-xt","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["amd-radeon-rx-7800-xt","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"8",null],["amd-radeon-rx-7800-xt","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,"4",null],["amd-radeon-rx-7800-xt","glm-4-6v-flash","rocm","fits","Q8_0",8192,10.8,101888,false,null,null,null],["amd-radeon-rx-7800-xt","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","glm-4-7-flash","rocm","fits","Q2_K",8192,12.77,44032,false,null,null,null],["amd-radeon-rx-7800-xt","glm-4-7-flash-reap-23b-a3b","rocm","fits","Q4_0",8192,14.61,10752,false,null,null,null],["amd-radeon-rx-7800-xt","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"7",null],["amd-radeon-rx-7800-xt","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"6",null],["amd-radeon-rx-7800-xt","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-rx-7800-xt","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["amd-radeon-rx-7800-xt","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7800-xt","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7800-xt","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-rx-7800-xt","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,"6",null],["amd-radeon-rx-7800-xt","gpt-oss-20b","rocm","fits","Q8_0",8192,12.9,78848,false,null,null,null],["amd-radeon-rx-7800-xt","granite-3-3-8b-instruct","rocm","fits","Q8_0",8192,11.11,30464,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-0-1b","rocm","fits","BF16",8192,5.14,124928,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-0-350m","rocm","fits","BF16",8192,2.2,32768,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-0-h-1b","rocm","fits","BF16",8192,4.44,131072,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-0-h-350m","rocm","fits","BF16",8192,2.07,32768,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-1-30b","rocm","fits","Q2_K",8192,13.89,11264,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-1-3b","rocm","fits","BF16",8192,8.61,82688,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-1-8b","rocm","fits","Q8_0",8192,11.33,29184,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-2-30b","rocm","fits","Q2_K",8192,13.89,11264,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-2-3b","rocm","fits","BF16",8192,8.61,82688,false,null,null,null],["amd-radeon-rx-7800-xt","granite-4-2-8b","rocm","fits","Q8_0",8192,11.33,29184,false,null,null,null],["amd-radeon-rx-7800-xt","granite-guardian-3-2-8b-factuality-detection","rocm","fits","Q8_0",8192,11.11,30464,false,null,null,null],["amd-radeon-rx-7800-xt","granite-guardian-4-0-3b-toxicity-ja","rocm","fits","Q6_K",8192,4.67,130560,false,null,null,null],["amd-radeon-rx-7800-xt","granite-guardian-4-1-8b","rocm","fits","Q8_0",8192,11.33,29184,false,null,null,null],["amd-radeon-rx-7800-xt","granite-vision-4-1-4b","rocm","fits","BF16",8192,8.61,82688,false,null,null,null],["amd-radeon-rx-7800-xt","harc-llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,57088,false,null,null,null],["amd-radeon-rx-7800-xt","harc-qwen2-5-7b-instruct","rocm","fits","Q6_K",8192,7.47,32768,false,null,null,null],["amd-radeon-rx-7800-xt","hermes-4-3-36b","rocm","fits","IQ2_XXS",8192,12.89,15360,false,null,null,null],["amd-radeon-rx-7800-xt","hipo-1-7b","rocm","fits","Q6_K",8192,3.63,40960,false,null,null,null],["amd-radeon-rx-7800-xt","holo-3-1-0-8b","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7800-xt","holo-3-1-35b-a3b","rocm","fits","Q2_K",8192,14.45,21760,false,null,null,null],["amd-radeon-rx-7800-xt","holo-3-1-4b","rocm","fits","F16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","holo-3-1-9b","rocm","fits","Q8_0",8192,10.25,139776,false,null,null,null],["amd-radeon-rx-7800-xt","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7800-xt","holo2-30b-a3b","rocm","fits","Q2_K",8192,13.04,25344,false,null,null,null],["amd-radeon-rx-7800-xt","holo2-4b","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","holo2-8b","rocm","fits","Q6_K",8192,8.59,50176,false,null,null,null],["amd-radeon-rx-7800-xt","holo3-35b-a3b","rocm","fits","Q2_K",8192,14.45,21760,false,null,null,null],["amd-radeon-rx-7800-xt","holo4-27b","rocm","fits","IQ3_XXS",8192,13.08,33280,false,null,null,null],["amd-radeon-rx-7800-xt","holo4-35b-a3b","rocm","fits","IQ2_M",8192,14.37,25344,false,null,null,null],["amd-radeon-rx-7800-xt","holotron4-30b-a3b","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7800-xt","hunyuanocr","rocm","fits","F16",8192,3.13,32768,false,null,null,null],["amd-radeon-rx-7800-xt","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"7",null],["amd-radeon-rx-7800-xt","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,"3",null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-llama3-8b-baseline","rocm","fits","Q8_0",8192,10.15,43264,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.15,43264,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.15,43264,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-llama3-8b-multiview","rocm","fits","Q8_0",8192,10.15,43264,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-4b-baseline","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-4b-multiview","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-8b-baseline","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intent-aware-lfqa-qwen3-8b-multiview","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","ising-calibration-1-35b-a3b","rocm","fits","Q2_K",8192,14.45,21760,false,null,null,null],["amd-radeon-rx-7800-xt","ising-calibration-1-5-31b-bf16","rocm","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["amd-radeon-rx-7800-xt","januscoder-14b","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","januscoder-8b","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7800-xt","januscoderv-7b","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","kanana-2-3b-base","rocm","fits","Q6_K",8192,4.89,32768,false,null,null,null],["amd-radeon-rx-7800-xt","kanana-2-3b-instruct","rocm","fits","F16",8192,8.57,32768,false,null,null,null],["amd-radeon-rx-7800-xt","kat-coder-v2-5-dev","rocm","fits","Q2_K",8192,14.13,36096,false,null,null,null],["amd-radeon-rx-7800-xt","kat-dev-72b-exp","rocm","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["amd-radeon-rx-7800-xt","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-rx-7800-xt","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-rx-7800-xt","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-rx-7800-xt","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-rx-7800-xt","kimi-linear-48b-a3b-base","rocm","fits","IQ2_XXS",8192,14.24,59904,false,null,null,null],["amd-radeon-rx-7800-xt","kimi-linear-48b-a3b-instruct","rocm","fits","IQ2_XXS",8192,13.35,149504,false,null,null,null],["amd-radeon-rx-7800-xt","kimi-linear-reap-35b-a3b-instruct","rocm","fits","Q2_K",8192,14.15,68352,false,null,null,null],["amd-radeon-rx-7800-xt","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","laguna-xs-2-1","rocm","fits","Q2_K",8192,13.77,31232,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-2-6b-exp","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-2-6b-longevity","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-2-6b-transcript","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-24b-a2b","rocm","fits","Q4_0",8192,14.65,12800,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-1-2b-base","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-1-2b-instruct","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-1-2b-jp","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-1-2b-jp-202606","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-1-2b-thinking","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-2-6b","rocm","fits","BF16",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-2-6b-base","rocm","fits","Q6_K",8192,3.58,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-230m","rocm","fits","BF16",8192,1.83,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-24b-a2b","rocm","fits","Q4_0",8192,14.75,8192,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-350m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-8b-a1b","rocm","fits","Q8_0",8192,10.2,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-encoder-350m-diffusion","rocm","fits","Q6_K",8192,1.66,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-vl-1-6b","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-vl-1-6b-extract","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-vl-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-vl-450m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-5-vl-450m-extract","rocm","fits","F16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-8b-a1b","rocm","fits","Q8_0",8192,10.07,128000,false,null,null,null],["amd-radeon-rx-7800-xt","lfm2-vl-3b","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7800-xt","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-rx-7800-xt","llama-3-1-70b-instruct","rocm","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["amd-radeon-rx-7800-xt","llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,57088,false,null,null,null],["amd-radeon-rx-7800-xt","llama-3-2-1b-instruct","rocm","fits","BF16",8192,3.97,131072,false,null,null,null],["amd-radeon-rx-7800-xt","llama-3-2-3b-instruct","rocm","fits","BF16",8192,8.5,62720,false,null,null,null],["amd-radeon-rx-7800-xt","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,"3",null],["amd-radeon-rx-7800-xt","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,"4",null],["amd-radeon-rx-7800-xt","mathform-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","medgemma-1-5-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-1-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,52992,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-12b-a2-5b-base","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-12b-a2-5b-instruct","rocm","fits","Q8_0",8192,14.03,52992,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-12b-a2-5b-instruct-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,52992,false,null,null,null],["amd-radeon-rx-7800-xt","mellum2-12b-a2-5b-thinking-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7800-xt","mimo-embodied-7b","rocm","fits","Q6_K",8192,8.14,53248,false,null,null,null],["amd-radeon-rx-7800-xt","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"8",null],["amd-radeon-rx-7800-xt","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-rx-7800-xt","mimo-v2-6-distill-qwen-9b","rocm","fits","Q8_0",8192,10.27,139264,false,null,null,null],["amd-radeon-rx-7800-xt","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7800-xt","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7800-xt","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","minicpm-o-4-5","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm-v-4-6","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm-v-4-6-thinking","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm-v-4-7-1b","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm-v-4-7-35b-a3b","rocm","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["amd-radeon-rx-7800-xt","minicpm5-1b","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm5-1b-base","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm5-1b-sft","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm5-2b","rocm","fits","BF16",8192,6.04,131072,false,null,null,null],["amd-radeon-rx-7800-xt","minicpm5-2b-base","rocm","fits","Q6_K",8192,3.43,262144,true,null,null,null],["amd-radeon-rx-7800-xt","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"7",null],["amd-radeon-rx-7800-xt","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"7",null],["amd-radeon-rx-7800-xt","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"7",null],["amd-radeon-rx-7800-xt","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["amd-radeon-rx-7800-xt","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,"5",null],["amd-radeon-rx-7800-xt","ministral-3-14b-instruct-2512","rocm","fits","Q5_K_M",8192,11.57,27648,false,null,null,null],["amd-radeon-rx-7800-xt","ministral-3-14b-reasoning-2512","rocm","fits","Q5_K_M",8192,11.57,27648,false,null,null,null],["amd-radeon-rx-7800-xt","ministral-3-3b-instruct-2512","rocm","fits","BF16",8192,8.86,63488,false,null,null,null],["amd-radeon-rx-7800-xt","ministral-3-3b-reasoning-2512","rocm","fits","BF16",8192,8.86,63488,false,null,null,null],["amd-radeon-rx-7800-xt","ministral-3-8b-instruct-2512","rocm","fits","Q8_0",8192,10.68,37376,false,null,null,null],["amd-radeon-rx-7800-xt","ministral-3-8b-reasoning-2512","rocm","fits","Q8_0",8192,10.68,37376,false,null,null,null],["amd-radeon-rx-7800-xt","mistral-7b-instruct-v0-2","rocm","fits","Q6_K",8192,8.05,32768,false,null,null,null],["amd-radeon-rx-7800-xt","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-rx-7800-xt","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,"4",null],["amd-radeon-rx-7800-xt","mistral-nemo-instruct-2407","rocm","fits","Q8_0",8192,14.65,8704,false,null,null,null],["amd-radeon-rx-7800-xt","mistral-small-3-2-24b-instruct-2506","rocm","fits","IQ4_XS",8192,14.75,8192,false,null,null,null],["amd-radeon-rx-7800-xt","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,"3",null],["amd-radeon-rx-7800-xt","muse-glimmer-30b","rocm","fits","IQ3_XXS",8192,12.61,131072,false,null,null,null],["amd-radeon-rx-7800-xt","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-rx-7800-xt","nemotron-3-content-safety","rocm","fits","Q6_K",8192,5.37,131072,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","no","Q4_K_M",8192,23.26,null,null,null,"2",null],["amd-radeon-rx-7800-xt","nemotron-cascade-14b-thinking","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-cascade-2-30b-a3b","rocm","tight","Q4_0",8192,19.24,null,null,null,null,null],["amd-radeon-rx-7800-xt","nemotron-cascade-8b","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-cascade-8b-thinking","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-orchestrator-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-terminal-14b","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-terminal-32b","rocm","fits","IQ2_M",8192,14.23,9984,false,null,null,null],["amd-radeon-rx-7800-xt","nemotron-terminal-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7800-xt","north-mini-code-1-0","rocm","fits","Q2_K",8192,13.23,39168,false,null,null,null],["amd-radeon-rx-7800-xt","nouscoder-14b","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.27,null,null,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,"6",null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.18,null,null,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-nano-4b-bf16","rocm","fits","BF16",8192,8.73,262144,false,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,"4",null],["amd-radeon-rx-7800-xt","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,"4",null],["amd-radeon-rx-7800-xt","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7800-xt","nvidia-nemotron-nano-9b-v2","rocm","fits","Q8_0",8192,10.63,131072,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1-32b-instruct","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1-32b-instruct-dpo","rocm","fits","IQ2_M",8192,13.93,11264,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1-32b-think","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1-7b-rl-zero-math","rocm","fits","Q8_0",8192,12.68,12032,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-1125-32b","rocm","fits","IQ2_M",8192,13.93,11264,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-32b-think","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-32b-think-dpo","rocm","fits","IQ2_M",8192,13.93,11264,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-32b-think-sft","rocm","fits","IQ2_M",8192,13.93,11264,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-instruct","rocm","fits","Q8_0",8192,12.68,12032,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-instruct-dpo","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-instruct-sft","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-rl-zero-general","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-rl-zero-if","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-rl-zero-math","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-rl-zero-mix","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-think","rocm","fits","Q8_0",8192,12.68,12032,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-think-dpo","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmo-3-7b-think-sft","rocm","fits","Q6_K",8192,11.05,15104,false,null,null,null],["amd-radeon-rx-7800-xt","olmocr-2-7b-1025","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","optimind-sft","rocm","fits","Q4_0",8192,13.22,66560,false,null,null,null],["amd-radeon-rx-7800-xt","phi-3-5-mini-instruct","rocm","fits","Q8_0",8192,8.32,24576,false,null,null,null],["amd-radeon-rx-7800-xt","phi-4","rocm","fits","Q6_K",8192,14.3,10240,false,null,null,null],["amd-radeon-rx-7800-xt","phi-4-mini-instruct","rocm","fits","BF16",8192,9.99,44544,false,null,null,null],["amd-radeon-rx-7800-xt","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,"3",null],["amd-radeon-rx-7800-xt","qwen2-5-14b-instruct","rocm","fits","Q6_K",8192,14.16,11008,false,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-32b-instruct","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-3b-instruct","rocm","fits","Q8_0",8192,4.83,32768,false,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,"3",null],["amd-radeon-rx-7800-xt","qwen2-5-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-coder-32b-instruct","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-coder-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-vl-7b-instruct","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","qwen2-5-vl-7b-surg-cholect50","rocm","fits","Q8_0",8192,9.15,104192,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-0-6b","rocm","fits","BF16",8192,3.41,40960,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-1-7b","rocm","fits","BF16",8192,5.62,40960,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-14b","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"7",null],["amd-radeon-rx-7800-xt","qwen3-30b-a3b","rocm","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["amd-radeon-rx-7800-xt","qwen3-30b-a3b-instruct-2507","rocm","fits","Q2_K",8192,13.04,25344,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-32b","rocm","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["amd-radeon-rx-7800-xt","qwen3-4b","rocm","fits","Q8_0",8192,6.7,40960,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-4b-instruct-2507","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-0-8b","rocm","fits","BF16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-0-8b-base","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,"3",null],["amd-radeon-rx-7800-xt","qwen3-5-27b","rocm","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-2b","rocm","fits","BF16",8192,5.38,262144,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-2b-base","rocm","fits","Q6_K",8192,3.21,262144,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-35b-a3b","rocm","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-35b-a3b-base","rocm","fits","Q2_K",8192,14.33,26880,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["amd-radeon-rx-7800-xt","qwen3-5-4b","rocm","fits","BF16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-4b-base","rocm","fits","F16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-9b","rocm","fits","Q8_0",8192,10.25,139776,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-5-9b-base","rocm","fits","Q8_0",8192,10.25,139776,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-6-27b","rocm","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen3-6-35b-a3b","rocm","fits","Q2_K",8192,14.12,36352,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-rx-7800-xt","qwen3-8-27b","rocm","fits","IQ3_XXS",8192,13.79,22528,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-8-3-6-27b-blend","rocm","fits","IQ3_XXS",8192,13.79,22528,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-coder-30b-a3b-instruct","rocm","fits","Q2_K",8192,13.04,25344,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"over",null],["amd-radeon-rx-7800-xt","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,"3",null],["amd-radeon-rx-7800-xt","qwen3-coder-next-base","rocm","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["amd-radeon-rx-7800-xt","qwen3-coder-reap-25b-a3b","rocm","fits","Q3_K_M",8192,13.26,23296,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","qwen3-nemotron-14b-brrm","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7800-xt","qwen3-nemotron-8b-brrm","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,"3",null],["amd-radeon-rx-7800-xt","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"7",null],["amd-radeon-rx-7800-xt","qwen3-vl-2b-instruct","rocm","fits","BF16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-2b-thinking","rocm","fits","BF16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-30b-a3b-instruct","rocm","fits","Q2_K",8192,13.04,25344,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-32b-instruct","rocm","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-32b-thinking","rocm","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-4b-instruct","rocm","fits","BF16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-4b-thinking","rocm","fits","BF16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-8b-instruct","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwen3-vl-8b-thinking","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","qwq-32b","rocm","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["amd-radeon-rx-7800-xt","riva-translate-4b-instruct-v1-1","rocm","fits","Q6_K",8192,5.97,8192,false,null,null,null],["amd-radeon-rx-7800-xt","rlvr-8b-0926","rocm","fits","Q6_K",8192,8.59,50176,false,null,null,null],["amd-radeon-rx-7800-xt","rnj-1-instruct","rocm","fits","Q8_0",8192,10.99,32768,false,null,null,null],["amd-radeon-rx-7800-xt","sera-32b","rocm","fits","IQ2_M",8192,14.23,9984,false,null,null,null],["amd-radeon-rx-7800-xt","singguard-2b","rocm","fits","F16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","smollm3-3b","rocm","fits","BF16",8192,7.9,65536,false,null,null,null],["amd-radeon-rx-7800-xt","smollm3-3b-gsm8k-sft","rocm","fits","Q6_K",8192,4.35,65536,false,null,null,null],["amd-radeon-rx-7800-xt","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["amd-radeon-rx-7800-xt","spatial-ssrl-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7800-xt","spatial-ssrl-qwen3vl-4b","rocm","fits","F16",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,"4",null],["amd-radeon-rx-7800-xt","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["amd-radeon-rx-7800-xt","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["amd-radeon-rx-7800-xt","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"7",null],["amd-radeon-rx-7800-xt","step3-vl-10b-base","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7800-xt","tiny-aya-earth","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7800-xt","tiny-aya-fire","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7800-xt","tiny-aya-global","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7800-xt","tiny-aya-water","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7800-xt","translategemma-12b-it","rocm","fits","Q6_K",8192,13.02,34048,false,null,null,null],["amd-radeon-rx-7800-xt","translategemma-27b-it","rocm","fits","Q2_K",8192,14.43,12032,false,null,null,null],["amd-radeon-rx-7800-xt","translategemma-4b-it","rocm","fits","F16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7800-xt","trinity-mini","rocm","fits","Q3_K_M",8192,13.65,67584,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-mini-base","rocm","fits","Q3_K_M",8192,14.08,43776,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-mini-base-pre-anneal","rocm","fits","Q3_K_M",4096,13.8,4096,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-nano-base","rocm","fits","Q6_K",8192,6.67,131072,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-nano-base-pre-anneal","rocm","fits","Q6_K",4096,6.43,4096,false,null,null,null],["amd-radeon-rx-7800-xt","trinity-nano-preview","rocm","fits","BF16",8192,13.51,83968,false,null,null,null],["amd-radeon-rx-7800-xt","ui-mate-27b","rocm","fits","IQ3_XXS",8192,14.25,15616,false,null,null,null],["amd-radeon-rx-7800-xt","ui-mate-9b","rocm","fits","Q8_0",8192,10.27,139264,false,null,null,null],["amd-radeon-rx-7800-xt","ui-mate-democua-27b","rocm","fits","Q2_K",8192,12.74,38400,false,null,null,null],["amd-radeon-rx-7800-xt","ui-venus-1-5-2b","rocm","fits","F16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","ui-venus-1-5-30b-a3b","rocm","fits","Q2_K",8192,13.04,25344,false,null,null,null],["amd-radeon-rx-7800-xt","ui-venus-1-5-8b","rocm","fits","Q6_K",8192,8.59,50176,false,null,null,null],["amd-radeon-rx-7800-xt","ui-venus-2-9b","rocm","fits","Q8_0",8192,10.27,139264,false,null,null,null],["amd-radeon-rx-7800-xt","userrepgen-4b","rocm","fits","BF16",8192,10.23,140288,false,null,null,null],["amd-radeon-rx-7800-xt","webworld-14b","rocm","fits","Q6_K",8192,13.89,13312,false,null,null,null],["amd-radeon-rx-7800-xt","webworld-32b","rocm","fits","IQ2_M",8192,14.23,9984,false,null,null,null],["amd-radeon-rx-7800-xt","webworld-8b","rocm","fits","Q8_0",8192,10.39,37888,false,null,null,null],["amd-radeon-rx-7800-xt","x-reasoner-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7800-xt","youtu-llm-2b","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7800-xt","youtu-llm-2b-base","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7800-xt","youtu-vl-4b-instruct","rocm","fits","Q6_K",8192,5.91,32768,false,null,null,null],["amd-radeon-rx-7800-xt","zwz-2b","rocm","fits","F16",8192,5.62,87808,false,null,null,null],["amd-radeon-rx-7800-xt","zwz-4b","rocm","fits","Q6_K",8192,5.74,69632,false,null,null,null],["amd-radeon-rx-7800-xt","zwz-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7800-xt","zwz-8b","rocm","fits","Q6_K",8192,8.59,50176,false,null,null,null],["amd-radeon-rx-7900-gre","aescode-32b","rocm","fits","IQ2_XXS",8192,13.6,12032,false,null,null,null],["amd-radeon-rx-7900-gre","aescode-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","agentcpm-explore","rocm","fits","Q6_K",8192,5.74,68608,false,null,null,null],["amd-radeon-rx-7900-gre","ai21-jamba-reasoning-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-gre","ai21-jamba2-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-gre","ai21-jamba2-mini","rocm","fits","IQ2_XXS",8192,13.63,63232,false,null,null,null],["amd-radeon-rx-7900-gre","apertus-v1-1-1-5b","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-gre","apertus-v1-1-1-5b-instruct","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-gre","apertus-v1-1-4b","rocm","fits","Q6_K",4096,4.42,4096,false,null,null,null],["amd-radeon-rx-7900-gre","apriel-1-6-15b-thinker","rocm","fits","Q6_K",8192,13.92,11776,false,null,null,null],["amd-radeon-rx-7900-gre","aprielguard","rocm","fits","Q6_K",8192,7.87,76800,false,null,null,null],["amd-radeon-rx-7900-gre","armorocr","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","astabrief-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-gre","autoglm-phone-9b","rocm","fits","Q8_0",8192,10.8,65536,false,null,null,null],["amd-radeon-rx-7900-gre","autoglm-phone-9b-multilingual","rocm","fits","Q6_K",8192,9.25,65536,false,null,null,null],["amd-radeon-rx-7900-gre","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7900-gre","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-rx-7900-gre","bielik-11b-v3-0-instruct","rocm","fits","Q8_0",8192,14.42,8960,false,null,null,null],["amd-radeon-rx-7900-gre","bielik-minitron-7b-v3-0-instruct","rocm","fits","Q8_0",8192,10.25,32768,false,null,null,null],["amd-radeon-rx-7900-gre","bitcpm-cann-3b-unquantized","rocm","fits","Q6_K",8192,4.29,32768,false,null,null,null],["amd-radeon-rx-7900-gre","caprl-qwen3vl-2b","rocm","fits","F16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","caprl-qwen3vl-4b","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-rx-7900-gre","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,"6",null],["amd-radeon-rx-7900-gre","contextpilot-14b","rocm","fits","Q6_K",8192,14.34,9728,false,null,null,null],["amd-radeon-rx-7900-gre","contextpilot-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-gre","contextpilot-e4b","rocm","fits","F16",8192,10.89,131072,false,null,null,null],["amd-radeon-rx-7900-gre","cosmos-reason2-32b","rocm","fits","IQ2_M",8192,14.23,9472,false,null,null,null],["amd-radeon-rx-7900-gre","cosmos-reason2-8b","rocm","fits","Q6_K",8192,8.59,49152,false,null,null,null],["amd-radeon-rx-7900-gre","d1-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-gre","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-rx-7900-gre","deepseek-r1-0528-qwen3-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,"3",null],["amd-radeon-rx-7900-gre","deepseek-r1-distill-llama-8b","rocm","fits","Q8_0",8192,10.15,42240,false,null,null,null],["amd-radeon-rx-7900-gre","deepseek-r1-distill-qwen-14b","rocm","fits","Q6_K",8192,14.16,10496,false,null,null,null],["amd-radeon-rx-7900-gre","deepseek-r1-distill-qwen-32b","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7900-gre","deepseek-r1-distill-qwen-7b","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-rx-7900-gre","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-rx-7900-gre","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-rx-7900-gre","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,"4",null],["amd-radeon-rx-7900-gre","devstral-small-2-24b-instruct-2512","rocm","fits","Q3_K_M",8192,13.55,14592,false,null,null,null],["amd-radeon-rx-7900-gre","eurollm-22b-2512","rocm","fits","Q3_K_M",8192,13.62,12544,false,null,null,null],["amd-radeon-rx-7900-gre","eurollm-22b-instruct-2512","rocm","fits","Q3_K_M",8192,13.62,12544,false,null,null,null],["amd-radeon-rx-7900-gre","eurollm-9b-instruct-2512","rocm","fits","Q8_0",8192,11.65,25600,false,null,null,null],["amd-radeon-rx-7900-gre","euromoe-2-6b-a0-6b-instruct-2512","rocm","fits","Q6_K",8192,3.58,32768,false,null,null,null],["amd-radeon-rx-7900-gre","exaone-4-5-33b","rocm","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["amd-radeon-rx-7900-gre","fara-7b","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","fara1-5-27b","rocm","fits","IQ3_XXS",8192,14.25,13568,false,null,null,null],["amd-radeon-rx-7900-gre","fara1-5-4b","rocm","fits","BF16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","fara1-5-9b","rocm","fits","Q8_0",8192,10.27,135680,false,null,null,null],["amd-radeon-rx-7900-gre","frogboss-32b-2510","rocm","fits","IQ2_M",8192,14.23,9472,false,null,null,null],["amd-radeon-rx-7900-gre","frogmini-14b-2510","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","frognano-4b-2609","rocm","fits","BF16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","functiongemma-270m-it","rocm","fits","BF16",8192,2.14,32768,false,null,null,null],["amd-radeon-rx-7900-gre","gelab-zero-4b-preview","rocm","fits","BF16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-2-27b-it","rocm","fits","IQ2_M",8192,13.78,8192,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-2-9b-it","rocm","fits","Q6_K",8192,11.96,8192,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-3-12b-it","rocm","fits","Q6_K",8192,13.02,32256,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-3-1b-it","rocm","fits","BF16",8192,3.6,32768,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-3-27b-it","rocm","fits","Q2_K",8192,14.43,10496,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-3-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-12b","rocm","tight","Q8_0",8192,15.57,null,null,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-12b-it","rocm","fits","Q6_K",8192,12.74,112384,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-26b-a4b","rocm","fits","Q2_K",8192,13,81664,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-26b-a4b-it","rocm","fits","IQ3_XXS",8192,14.55,11520,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-31b","rocm","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-31b-it","rocm","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-e2b","rocm","fits","Q6_K",8192,3.49,131072,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-e2b-it","rocm","fits","BF16",8192,6.14,131072,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-e4b","rocm","fits","F16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-gre","gemma-4-e4b-it","rocm","fits","BF16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-gre","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,"4",null],["amd-radeon-rx-7900-gre","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["amd-radeon-rx-7900-gre","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,"4",null],["amd-radeon-rx-7900-gre","glm-4-6v-flash","rocm","fits","Q8_0",8192,10.8,98816,false,null,null,null],["amd-radeon-rx-7900-gre","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","glm-4-7-flash","rocm","fits","Q2_K",8192,12.77,41728,false,null,null,null],["amd-radeon-rx-7900-gre","glm-4-7-flash-reap-23b-a3b","rocm","fits","Q4_0",8192,14.61,8448,false,null,null,null],["amd-radeon-rx-7900-gre","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"7",null],["amd-radeon-rx-7900-gre","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"6",null],["amd-radeon-rx-7900-gre","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-rx-7900-gre","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["amd-radeon-rx-7900-gre","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-gre","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-gre","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-rx-7900-gre","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,"6",null],["amd-radeon-rx-7900-gre","gpt-oss-20b","rocm","fits","Q8_0",8192,12.9,74240,false,null,null,null],["amd-radeon-rx-7900-gre","granite-3-3-8b-instruct","rocm","fits","Q8_0",8192,11.11,29696,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-0-1b","rocm","fits","BF16",8192,5.14,123392,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-0-350m","rocm","fits","BF16",8192,2.2,32768,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-0-h-1b","rocm","fits","BF16",8192,4.44,131072,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-0-h-350m","rocm","fits","BF16",8192,2.07,32768,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-1-30b","rocm","fits","Q2_K",8192,13.89,11008,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-1-3b","rocm","fits","BF16",8192,8.61,81152,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-1-8b","rocm","fits","Q8_0",8192,11.33,28416,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-2-30b","rocm","fits","Q2_K",8192,13.89,11008,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-2-3b","rocm","fits","BF16",8192,8.61,81152,false,null,null,null],["amd-radeon-rx-7900-gre","granite-4-2-8b","rocm","fits","Q8_0",8192,11.33,28416,false,null,null,null],["amd-radeon-rx-7900-gre","granite-guardian-3-2-8b-factuality-detection","rocm","fits","Q8_0",8192,11.11,29696,false,null,null,null],["amd-radeon-rx-7900-gre","granite-guardian-4-0-3b-toxicity-ja","rocm","fits","Q6_K",8192,4.67,129024,false,null,null,null],["amd-radeon-rx-7900-gre","granite-guardian-4-1-8b","rocm","fits","Q8_0",8192,11.33,28416,false,null,null,null],["amd-radeon-rx-7900-gre","granite-vision-4-1-4b","rocm","fits","BF16",8192,8.61,81152,false,null,null,null],["amd-radeon-rx-7900-gre","harc-llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,56064,false,null,null,null],["amd-radeon-rx-7900-gre","harc-qwen2-5-7b-instruct","rocm","fits","Q6_K",8192,7.47,32768,false,null,null,null],["amd-radeon-rx-7900-gre","hermes-4-3-36b","rocm","fits","IQ2_XXS",8192,12.89,14848,false,null,null,null],["amd-radeon-rx-7900-gre","hipo-1-7b","rocm","fits","Q6_K",8192,3.63,40960,false,null,null,null],["amd-radeon-rx-7900-gre","holo-3-1-0-8b","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-gre","holo-3-1-35b-a3b","rocm","fits","Q2_K",8192,14.45,16128,false,null,null,null],["amd-radeon-rx-7900-gre","holo-3-1-4b","rocm","fits","F16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","holo-3-1-9b","rocm","fits","Q8_0",8192,10.25,136192,false,null,null,null],["amd-radeon-rx-7900-gre","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7900-gre","holo2-30b-a3b","rocm","fits","Q2_K",8192,13.04,24064,false,null,null,null],["amd-radeon-rx-7900-gre","holo2-4b","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","holo2-8b","rocm","fits","Q6_K",8192,8.59,49152,false,null,null,null],["amd-radeon-rx-7900-gre","holo3-35b-a3b","rocm","fits","Q2_K",8192,14.45,16128,false,null,null,null],["amd-radeon-rx-7900-gre","holo4-27b","rocm","fits","IQ3_XXS",8192,13.08,31488,false,null,null,null],["amd-radeon-rx-7900-gre","holo4-35b-a3b","rocm","fits","IQ2_M",8192,14.37,19456,false,null,null,null],["amd-radeon-rx-7900-gre","holotron4-30b-a3b","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-gre","hunyuanocr","rocm","fits","F16",8192,3.13,32768,false,null,null,null],["amd-radeon-rx-7900-gre","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"7",null],["amd-radeon-rx-7900-gre","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,"3",null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-llama3-8b-baseline","rocm","fits","Q8_0",8192,10.15,42240,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.15,42240,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.15,42240,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-llama3-8b-multiview","rocm","fits","Q8_0",8192,10.15,42240,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-4b-baseline","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-4b-multiview","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-8b-baseline","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intent-aware-lfqa-qwen3-8b-multiview","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","ising-calibration-1-35b-a3b","rocm","fits","Q2_K",8192,14.45,16128,false,null,null,null],["amd-radeon-rx-7900-gre","ising-calibration-1-5-31b-bf16","rocm","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["amd-radeon-rx-7900-gre","januscoder-14b","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","januscoder-8b","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7900-gre","januscoderv-7b","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","kanana-2-3b-base","rocm","fits","Q6_K",8192,4.89,32768,false,null,null,null],["amd-radeon-rx-7900-gre","kanana-2-3b-instruct","rocm","fits","F16",8192,8.57,32768,false,null,null,null],["amd-radeon-rx-7900-gre","kat-coder-v2-5-dev","rocm","fits","Q2_K",8192,14.13,30464,false,null,null,null],["amd-radeon-rx-7900-gre","kat-dev-72b-exp","rocm","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["amd-radeon-rx-7900-gre","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-rx-7900-gre","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-rx-7900-gre","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-rx-7900-gre","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-rx-7900-gre","kimi-linear-48b-a3b-base","rocm","fits","IQ2_XXS",8192,14.24,47360,false,null,null,null],["amd-radeon-rx-7900-gre","kimi-linear-48b-a3b-instruct","rocm","fits","IQ2_XXS",8192,13.35,136704,false,null,null,null],["amd-radeon-rx-7900-gre","kimi-linear-reap-35b-a3b-instruct","rocm","fits","Q2_K",8192,14.15,55808,false,null,null,null],["amd-radeon-rx-7900-gre","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","laguna-xs-2-1","rocm","fits","Q2_K",8192,13.77,28416,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-2-6b-exp","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-2-6b-longevity","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-2-6b-transcript","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-24b-a2b","rocm","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-1-2b-base","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-1-2b-instruct","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-1-2b-jp","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-1-2b-jp-202606","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-1-2b-thinking","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-2-6b","rocm","fits","BF16",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-2-6b-base","rocm","fits","Q6_K",8192,3.58,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-230m","rocm","fits","BF16",8192,1.83,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-24b-a2b","rocm","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-350m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-8b-a1b","rocm","fits","Q8_0",8192,10.2,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-encoder-350m-diffusion","rocm","fits","Q6_K",8192,1.66,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-vl-1-6b","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-vl-1-6b-extract","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-vl-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-vl-450m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-5-vl-450m-extract","rocm","fits","F16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-8b-a1b","rocm","fits","Q8_0",8192,10.07,128000,false,null,null,null],["amd-radeon-rx-7900-gre","lfm2-vl-3b","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-gre","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-rx-7900-gre","llama-3-1-70b-instruct","rocm","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["amd-radeon-rx-7900-gre","llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,56064,false,null,null,null],["amd-radeon-rx-7900-gre","llama-3-2-1b-instruct","rocm","fits","BF16",8192,3.97,131072,false,null,null,null],["amd-radeon-rx-7900-gre","llama-3-2-3b-instruct","rocm","fits","BF16",8192,8.5,61696,false,null,null,null],["amd-radeon-rx-7900-gre","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,"3",null],["amd-radeon-rx-7900-gre","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,"4",null],["amd-radeon-rx-7900-gre","mathform-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","medgemma-1-5-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-1-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,45056,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-12b-a2-5b-base","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-12b-a2-5b-instruct","rocm","fits","Q8_0",8192,14.03,45056,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-12b-a2-5b-instruct-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,45056,false,null,null,null],["amd-radeon-rx-7900-gre","mellum2-12b-a2-5b-thinking-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-gre","mimo-embodied-7b","rocm","fits","Q6_K",8192,8.14,52224,false,null,null,null],["amd-radeon-rx-7900-gre","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"8",null],["amd-radeon-rx-7900-gre","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-rx-7900-gre","mimo-v2-6-distill-qwen-9b","rocm","fits","Q8_0",8192,10.27,135680,false,null,null,null],["amd-radeon-rx-7900-gre","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-gre","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-gre","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","minicpm-o-4-5","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm-v-4-6","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm-v-4-6-thinking","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm-v-4-7-1b","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm-v-4-7-35b-a3b","rocm","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["amd-radeon-rx-7900-gre","minicpm5-1b","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm5-1b-base","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm5-1b-sft","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm5-2b","rocm","fits","BF16",8192,6.04,131072,false,null,null,null],["amd-radeon-rx-7900-gre","minicpm5-2b-base","rocm","fits","Q6_K",8192,3.43,261376,false,null,null,null],["amd-radeon-rx-7900-gre","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"8",null],["amd-radeon-rx-7900-gre","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"8",null],["amd-radeon-rx-7900-gre","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"8",null],["amd-radeon-rx-7900-gre","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["amd-radeon-rx-7900-gre","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,"5",null],["amd-radeon-rx-7900-gre","ministral-3-14b-instruct-2512","rocm","fits","Q5_K_M",8192,11.57,26880,false,null,null,null],["amd-radeon-rx-7900-gre","ministral-3-14b-reasoning-2512","rocm","fits","Q5_K_M",8192,11.57,26880,false,null,null,null],["amd-radeon-rx-7900-gre","ministral-3-3b-instruct-2512","rocm","fits","BF16",8192,8.86,62208,false,null,null,null],["amd-radeon-rx-7900-gre","ministral-3-3b-reasoning-2512","rocm","fits","BF16",8192,8.86,62208,false,null,null,null],["amd-radeon-rx-7900-gre","ministral-3-8b-instruct-2512","rocm","fits","Q8_0",8192,10.68,36608,false,null,null,null],["amd-radeon-rx-7900-gre","ministral-3-8b-reasoning-2512","rocm","fits","Q8_0",8192,10.68,36608,false,null,null,null],["amd-radeon-rx-7900-gre","mistral-7b-instruct-v0-2","rocm","fits","Q6_K",8192,8.05,32768,false,null,null,null],["amd-radeon-rx-7900-gre","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-rx-7900-gre","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,"4",null],["amd-radeon-rx-7900-gre","mistral-nemo-instruct-2407","rocm","fits","Q6_K",8192,11.91,24832,false,null,null,null],["amd-radeon-rx-7900-gre","mistral-small-3-2-24b-instruct-2506","rocm","fits","Q3_K_M",8192,13.55,14592,false,null,null,null],["amd-radeon-rx-7900-gre","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,"3",null],["amd-radeon-rx-7900-gre","muse-glimmer-30b","rocm","fits","IQ3_XXS",8192,12.61,131072,false,null,null,null],["amd-radeon-rx-7900-gre","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-rx-7900-gre","nemotron-3-content-safety","rocm","fits","Q6_K",8192,5.37,131072,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","no","Q4_K_M",8192,23.26,null,null,null,"2",null],["amd-radeon-rx-7900-gre","nemotron-cascade-14b-thinking","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-cascade-2-30b-a3b","rocm","tight","Q4_0",8192,19.24,null,null,null,null,null],["amd-radeon-rx-7900-gre","nemotron-cascade-8b","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-cascade-8b-thinking","rocm","fits","Q8_0",8192,10.39,32768,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-orchestrator-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-terminal-14b","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-terminal-32b","rocm","fits","IQ2_M",8192,14.23,9472,false,null,null,null],["amd-radeon-rx-7900-gre","nemotron-terminal-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-gre","north-mini-code-1-0","rocm","fits","Q2_K",8192,13.23,34816,false,null,null,null],["amd-radeon-rx-7900-gre","nouscoder-14b","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.27,null,null,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,"6",null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.18,null,null,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-nano-4b-bf16","rocm","fits","BF16",8192,8.73,262144,false,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,"4",null],["amd-radeon-rx-7900-gre","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,"4",null],["amd-radeon-rx-7900-gre","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-gre","nvidia-nemotron-nano-9b-v2","rocm","fits","Q8_0",8192,10.63,131072,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1-32b-instruct","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1-32b-instruct-dpo","rocm","fits","IQ2_M",8192,13.93,10752,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1-32b-think","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1-7b-rl-zero-math","rocm","fits","Q8_0",8192,12.68,11776,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-1125-32b","rocm","fits","IQ2_M",8192,13.93,10752,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-32b-think","rocm","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-32b-think-dpo","rocm","fits","IQ2_M",8192,13.93,10752,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-32b-think-sft","rocm","fits","IQ2_M",8192,13.93,10752,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-instruct","rocm","fits","Q8_0",8192,12.68,11776,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-instruct-dpo","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-instruct-sft","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-rl-zero-general","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-rl-zero-if","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-rl-zero-math","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-rl-zero-mix","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-think","rocm","fits","Q8_0",8192,12.68,11776,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-think-dpo","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmo-3-7b-think-sft","rocm","fits","Q6_K",8192,11.05,14848,false,null,null,null],["amd-radeon-rx-7900-gre","olmocr-2-7b-1025","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","optimind-sft","rocm","fits","Q4_0",8192,13.22,61952,false,null,null,null],["amd-radeon-rx-7900-gre","phi-3-5-mini-instruct","rocm","fits","Q8_0",8192,8.32,24320,false,null,null,null],["amd-radeon-rx-7900-gre","phi-4","rocm","fits","Q6_K",8192,14.3,9728,false,null,null,null],["amd-radeon-rx-7900-gre","phi-4-mini-instruct","rocm","fits","BF16",8192,9.99,43520,false,null,null,null],["amd-radeon-rx-7900-gre","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,"3",null],["amd-radeon-rx-7900-gre","qwen2-5-14b-instruct","rocm","fits","Q6_K",8192,14.16,10496,false,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-32b-instruct","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-3b-instruct","rocm","fits","Q8_0",8192,4.83,32768,false,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,"3",null],["amd-radeon-rx-7900-gre","qwen2-5-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-coder-32b-instruct","rocm","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-coder-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-vl-7b-instruct","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen2-5-vl-7b-surg-cholect50","rocm","fits","Q8_0",8192,9.15,102144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-0-6b","rocm","fits","BF16",8192,3.41,40960,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-1-7b","rocm","fits","BF16",8192,5.62,40960,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-14b","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"7",null],["amd-radeon-rx-7900-gre","qwen3-30b-a3b","rocm","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["amd-radeon-rx-7900-gre","qwen3-30b-a3b-instruct-2507","rocm","fits","Q2_K",8192,13.04,24064,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-32b","rocm","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["amd-radeon-rx-7900-gre","qwen3-4b","rocm","fits","Q8_0",8192,6.7,40960,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-4b-instruct-2507","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-0-8b","rocm","fits","BF16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-0-8b-base","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,"3",null],["amd-radeon-rx-7900-gre","qwen3-5-27b","rocm","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-2b","rocm","fits","BF16",8192,5.38,262144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-2b-base","rocm","fits","Q6_K",8192,3.21,262144,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-35b-a3b","rocm","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-35b-a3b-base","rocm","fits","Q2_K",8192,14.33,21248,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["amd-radeon-rx-7900-gre","qwen3-5-4b","rocm","fits","BF16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-4b-base","rocm","fits","F16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-9b","rocm","fits","Q8_0",8192,10.25,136192,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-5-9b-base","rocm","fits","Q8_0",8192,10.25,136192,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-6-27b","rocm","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen3-6-35b-a3b","rocm","fits","Q2_K",8192,14.12,30720,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-rx-7900-gre","qwen3-8-27b","rocm","fits","IQ3_XXS",8192,13.79,20736,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-8-3-6-27b-blend","rocm","fits","IQ3_XXS",8192,13.79,20736,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-coder-30b-a3b-instruct","rocm","fits","Q2_K",8192,13.04,24064,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"over",null],["amd-radeon-rx-7900-gre","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,"3",null],["amd-radeon-rx-7900-gre","qwen3-coder-next-base","rocm","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["amd-radeon-rx-7900-gre","qwen3-coder-reap-25b-a3b","rocm","fits","Q3_K_M",8192,13.26,22016,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","qwen3-nemotron-14b-brrm","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["amd-radeon-rx-7900-gre","qwen3-nemotron-8b-brrm","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,"3",null],["amd-radeon-rx-7900-gre","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"7",null],["amd-radeon-rx-7900-gre","qwen3-vl-2b-instruct","rocm","fits","BF16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-2b-thinking","rocm","fits","BF16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-30b-a3b-instruct","rocm","fits","Q2_K",8192,13.04,24064,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-32b-instruct","rocm","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-32b-thinking","rocm","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-4b-instruct","rocm","fits","BF16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-4b-thinking","rocm","fits","BF16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-8b-instruct","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwen3-vl-8b-thinking","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","qwq-32b","rocm","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["amd-radeon-rx-7900-gre","riva-translate-4b-instruct-v1-1","rocm","fits","Q6_K",8192,5.97,8192,false,null,null,null],["amd-radeon-rx-7900-gre","rlvr-8b-0926","rocm","fits","Q6_K",8192,8.59,49152,false,null,null,null],["amd-radeon-rx-7900-gre","rnj-1-instruct","rocm","fits","Q8_0",8192,10.99,32768,false,null,null,null],["amd-radeon-rx-7900-gre","sera-32b","rocm","fits","IQ2_M",8192,14.23,9472,false,null,null,null],["amd-radeon-rx-7900-gre","singguard-2b","rocm","fits","F16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","smollm3-3b","rocm","fits","BF16",8192,7.9,65536,false,null,null,null],["amd-radeon-rx-7900-gre","smollm3-3b-gsm8k-sft","rocm","fits","Q6_K",8192,4.35,65536,false,null,null,null],["amd-radeon-rx-7900-gre","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["amd-radeon-rx-7900-gre","spatial-ssrl-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-gre","spatial-ssrl-qwen3vl-4b","rocm","fits","F16",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,"4",null],["amd-radeon-rx-7900-gre","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["amd-radeon-rx-7900-gre","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["amd-radeon-rx-7900-gre","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"7",null],["amd-radeon-rx-7900-gre","step3-vl-10b-base","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-gre","tiny-aya-earth","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-gre","tiny-aya-fire","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-gre","tiny-aya-global","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-gre","tiny-aya-water","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-gre","translategemma-12b-it","rocm","fits","Q6_K",8192,13.02,32256,false,null,null,null],["amd-radeon-rx-7900-gre","translategemma-27b-it","rocm","fits","Q2_K",8192,14.43,10496,false,null,null,null],["amd-radeon-rx-7900-gre","translategemma-4b-it","rocm","fits","F16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["amd-radeon-rx-7900-gre","trinity-mini","rocm","fits","Q3_K_M",8192,13.65,60672,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-mini-base","rocm","fits","Q3_K_M",8192,14.08,36864,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-mini-base-pre-anneal","rocm","fits","Q3_K_M",4096,13.8,4096,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-nano-base","rocm","fits","Q6_K",8192,6.67,131072,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-nano-base-pre-anneal","rocm","fits","Q6_K",4096,6.43,4096,false,null,null,null],["amd-radeon-rx-7900-gre","trinity-nano-preview","rocm","fits","BF16",8192,13.51,76288,false,null,null,null],["amd-radeon-rx-7900-gre","ui-mate-27b","rocm","fits","IQ3_XXS",8192,14.25,13568,false,null,null,null],["amd-radeon-rx-7900-gre","ui-mate-9b","rocm","fits","Q8_0",8192,10.27,135680,false,null,null,null],["amd-radeon-rx-7900-gre","ui-mate-democua-27b","rocm","fits","Q2_K",8192,12.74,36608,false,null,null,null],["amd-radeon-rx-7900-gre","ui-venus-1-5-2b","rocm","fits","F16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","ui-venus-1-5-30b-a3b","rocm","fits","Q2_K",8192,13.04,24064,false,null,null,null],["amd-radeon-rx-7900-gre","ui-venus-1-5-8b","rocm","fits","Q6_K",8192,8.59,49152,false,null,null,null],["amd-radeon-rx-7900-gre","ui-venus-2-9b","rocm","fits","Q8_0",8192,10.27,135680,false,null,null,null],["amd-radeon-rx-7900-gre","userrepgen-4b","rocm","fits","BF16",8192,10.23,136704,false,null,null,null],["amd-radeon-rx-7900-gre","webworld-14b","rocm","fits","Q6_K",8192,13.89,12544,false,null,null,null],["amd-radeon-rx-7900-gre","webworld-32b","rocm","fits","IQ2_M",8192,14.23,9472,false,null,null,null],["amd-radeon-rx-7900-gre","webworld-8b","rocm","fits","Q8_0",8192,10.39,36864,false,null,null,null],["amd-radeon-rx-7900-gre","x-reasoner-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-gre","youtu-llm-2b","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-gre","youtu-llm-2b-base","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-gre","youtu-vl-4b-instruct","rocm","fits","Q6_K",8192,5.91,32768,false,null,null,null],["amd-radeon-rx-7900-gre","zwz-2b","rocm","fits","F16",8192,5.62,86784,false,null,null,null],["amd-radeon-rx-7900-gre","zwz-4b","rocm","fits","Q6_K",8192,5.74,68608,false,null,null,null],["amd-radeon-rx-7900-gre","zwz-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-gre","zwz-8b","rocm","fits","Q6_K",8192,8.59,49152,false,null,null,null],["amd-radeon-rx-7900-xt","aescode-32b","rocm","fits","IQ3_XXS",8192,16.42,16640,false,null,null,null],["amd-radeon-rx-7900-xt","aescode-8b","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","agentcpm-explore","rocm","fits","Q6_K",8192,5.74,96000,false,null,null,null],["amd-radeon-rx-7900-xt","ai21-jamba-reasoning-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-xt","ai21-jamba2-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-xt","ai21-jamba2-mini","rocm","fits","IQ2_M",8192,17.29,81920,false,null,null,null],["amd-radeon-rx-7900-xt","apertus-v1-1-1-5b","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-xt","apertus-v1-1-1-5b-instruct","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-xt","apertus-v1-1-4b","rocm","fits","Q6_K",4096,4.42,4096,false,null,null,null],["amd-radeon-rx-7900-xt","apriel-1-6-15b-thinker","rocm","fits","Q8_0",8192,17.19,15360,false,null,null,null],["amd-radeon-rx-7900-xt","aprielguard","rocm","fits","Q6_K",8192,7.87,117248,false,null,null,null],["amd-radeon-rx-7900-xt","armorocr","rocm","fits","Q8_0",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","astabrief-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xt","autoglm-phone-9b","rocm","fits","Q8_0",8192,10.8,65536,false,null,null,null],["amd-radeon-rx-7900-xt","autoglm-phone-9b-multilingual","rocm","fits","Q6_K",8192,9.25,65536,false,null,null,null],["amd-radeon-rx-7900-xt","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["amd-radeon-rx-7900-xt","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-rx-7900-xt","bielik-11b-v3-0-instruct","rocm","fits","Q8_0",8192,14.42,28672,false,null,null,null],["amd-radeon-rx-7900-xt","bielik-minitron-7b-v3-0-instruct","rocm","fits","Q8_0",8192,10.25,32768,false,null,null,null],["amd-radeon-rx-7900-xt","bitcpm-cann-3b-unquantized","rocm","fits","Q6_K",8192,4.29,32768,false,null,null,null],["amd-radeon-rx-7900-xt","caprl-qwen3vl-2b","rocm","fits","F16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","caprl-qwen3vl-4b","rocm","fits","F16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-rx-7900-xt","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,"5",null],["amd-radeon-rx-7900-xt","contextpilot-14b","rocm","fits","Q8_0",8192,17.21,16640,false,null,null,null],["amd-radeon-rx-7900-xt","contextpilot-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xt","contextpilot-e4b","rocm","fits","F16",8192,10.89,131072,false,null,null,null],["amd-radeon-rx-7900-xt","cosmos-reason2-32b","rocm","fits","IQ3_XXS",8192,15.66,19456,false,null,null,null],["amd-radeon-rx-7900-xt","cosmos-reason2-8b","rocm","fits","Q6_K",8192,8.59,76544,false,null,null,null],["amd-radeon-rx-7900-xt","d1-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-rx-7900-xt","deepseek-r1-0528-qwen3-8b","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,"2",null],["amd-radeon-rx-7900-xt","deepseek-r1-distill-llama-8b","rocm","fits","BF16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-r1-distill-qwen-14b","rocm","fits","Q8_0",8192,17.48,14080,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-r1-distill-qwen-32b","rocm","fits","Q2_K",8192,15.24,21248,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-r1-distill-qwen-7b","rocm","fits","F16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-rx-7900-xt","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-rx-7900-xt","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-rx-7900-xt","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,"3",null],["amd-radeon-rx-7900-xt","devstral-small-2-24b-instruct-2512","rocm","fits","Q5_K_M",8192,18.57,8448,false,null,null,null],["amd-radeon-rx-7900-xt","eurollm-22b-2512","rocm","fits","Q5_K_M",8192,18.25,9728,false,null,null,null],["amd-radeon-rx-7900-xt","eurollm-22b-instruct-2512","rocm","fits","Q5_K_M",8192,18.25,9728,false,null,null,null],["amd-radeon-rx-7900-xt","eurollm-9b-instruct-2512","rocm","fits","Q8_0",8192,11.65,32768,false,null,null,null],["amd-radeon-rx-7900-xt","euromoe-2-6b-a0-6b-instruct-2512","rocm","fits","Q6_K",8192,3.58,32768,false,null,null,null],["amd-radeon-rx-7900-xt","exaone-4-5-33b","rocm","tight","Q4_K_M",8192,22.33,null,null,null,null,null],["amd-radeon-rx-7900-xt","fara-7b","rocm","fits","BF16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","fara1-5-27b","rocm","fits","Q4_0",8192,17.74,21504,false,null,null,null],["amd-radeon-rx-7900-xt","fara1-5-4b","rocm","fits","BF16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","fara1-5-9b","rocm","fits","BF16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","frogboss-32b-2510","rocm","fits","IQ3_XXS",8192,15.66,19456,false,null,null,null],["amd-radeon-rx-7900-xt","frogmini-14b-2510","rocm","fits","Q6_K",8192,13.89,37120,false,null,null,null],["amd-radeon-rx-7900-xt","frognano-4b-2609","rocm","fits","BF16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","functiongemma-270m-it","rocm","fits","BF16",8192,2.14,32768,false,null,null,null],["amd-radeon-rx-7900-xt","gelab-zero-4b-preview","rocm","fits","BF16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-2-27b-it","rocm","fits","Q3_K_M",8192,17.73,8192,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-2-9b-it","rocm","fits","Q8_0",8192,14.78,8192,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-3-12b-it","rocm","fits","Q8_0",8192,15.82,50432,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-3-1b-it","rocm","fits","BF16",8192,3.6,32768,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-3-27b-it","rocm","fits","IQ4_XS",8192,18.61,8192,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-3-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-12b","rocm","fits","Q8_0",8192,15.57,177152,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-12b-it","rocm","fits","Q8_0",8192,15.57,177152,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-26b-a4b","rocm","fits","IQ4_XS",8192,16.41,108288,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-26b-a4b-it","rocm","fits","Q4_0",8192,17.1,77312,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-31b","rocm","fits","Q2_K",8192,17.58,20736,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-31b-it","rocm","tight","Q4_K_M",8192,23.86,null,null,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-e2b","rocm","fits","Q6_K",8192,3.49,131072,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-e2b-it","rocm","fits","BF16",8192,6.14,131072,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-e4b","rocm","fits","F16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-xt","gemma-4-e4b-it","rocm","fits","BF16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-xt","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,"3",null],["amd-radeon-rx-7900-xt","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,"2",null],["amd-radeon-rx-7900-xt","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"7",null],["amd-radeon-rx-7900-xt","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,"3",null],["amd-radeon-rx-7900-xt","glm-4-6v-flash","rocm","fits","Q8_0",8192,10.8,131072,false,null,null,null],["amd-radeon-rx-7900-xt","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","glm-4-7-flash","rocm","fits","Q4_0",8192,18.46,11008,false,null,null,null],["amd-radeon-rx-7900-xt","glm-4-7-flash-reap-23b-a3b","rocm","fits","Q5_K_M",8192,17.7,24832,false,null,null,null],["amd-radeon-rx-7900-xt","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"5",null],["amd-radeon-rx-7900-xt","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"5",null],["amd-radeon-rx-7900-xt","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-rx-7900-xt","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["amd-radeon-rx-7900-xt","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-xt","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-xt","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-rx-7900-xt","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"7",null],["amd-radeon-rx-7900-xt","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,"4",null],["amd-radeon-rx-7900-xt","gpt-oss-20b","rocm","fits","Q8_0",8192,12.9,131072,false,null,null,null],["amd-radeon-rx-7900-xt","granite-3-3-8b-instruct","rocm","fits","F16",8192,18.62,8192,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-0-1b","rocm","fits","BF16",8192,5.14,131072,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-0-350m","rocm","fits","BF16",8192,2.2,32768,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-0-h-1b","rocm","fits","BF16",8192,4.44,131072,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-0-h-350m","rocm","fits","BF16",8192,2.07,32768,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-1-30b","rocm","fits","Q3_K_M",8192,17.06,14080,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-1-3b","rocm","fits","BF16",8192,8.61,129792,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-1-8b","rocm","fits","Q8_0",8192,11.33,52992,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-2-30b","rocm","fits","Q3_K_M",8192,17.06,14080,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-2-3b","rocm","fits","BF16",8192,8.61,129792,false,null,null,null],["amd-radeon-rx-7900-xt","granite-4-2-8b","rocm","fits","Q8_0",8192,11.33,52992,false,null,null,null],["amd-radeon-rx-7900-xt","granite-guardian-3-2-8b-factuality-detection","rocm","fits","F16",8192,18.62,8192,false,null,null,null],["amd-radeon-rx-7900-xt","granite-guardian-4-0-3b-toxicity-ja","rocm","fits","Q6_K",8192,4.67,131072,false,null,null,null],["amd-radeon-rx-7900-xt","granite-guardian-4-1-8b","rocm","fits","Q8_0",8192,11.33,52992,false,null,null,null],["amd-radeon-rx-7900-xt","granite-vision-4-1-4b","rocm","fits","BF16",8192,8.61,129792,false,null,null,null],["amd-radeon-rx-7900-xt","harc-llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,86784,false,null,null,null],["amd-radeon-rx-7900-xt","harc-qwen2-5-7b-instruct","rocm","fits","Q6_K",8192,7.47,32768,false,null,null,null],["amd-radeon-rx-7900-xt","hermes-4-3-36b","rocm","fits","IQ3_XXS",8192,16.93,14592,false,null,null,null],["amd-radeon-rx-7900-xt","hipo-1-7b","rocm","fits","Q6_K",8192,3.63,40960,false,null,null,null],["amd-radeon-rx-7900-xt","holo-3-1-0-8b","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-xt","holo-3-1-35b-a3b","rocm","fits","Q3_K_M",8192,18.15,29696,false,null,null,null],["amd-radeon-rx-7900-xt","holo-3-1-4b","rocm","fits","F16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","holo-3-1-9b","rocm","fits","F16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["amd-radeon-rx-7900-xt","holo2-30b-a3b","rocm","fits","IQ4_XS",8192,18.17,12544,false,null,null,null],["amd-radeon-rx-7900-xt","holo2-4b","rocm","fits","F16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","holo2-8b","rocm","fits","Q6_K",8192,8.59,76544,false,null,null,null],["amd-radeon-rx-7900-xt","holo3-35b-a3b","rocm","fits","Q3_K_M",8192,18.15,29696,false,null,null,null],["amd-radeon-rx-7900-xt","holo4-27b","rocm","fits","Q4_K_M",8192,18.17,15104,false,null,null,null],["amd-radeon-rx-7900-xt","holo4-35b-a3b","rocm","fits","Q3_K_M",8192,18.4,18176,false,null,null,null],["amd-radeon-rx-7900-xt","holotron4-30b-a3b","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-xt","hunyuanocr","rocm","fits","F16",8192,3.13,32768,false,null,null,null],["amd-radeon-rx-7900-xt","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"5",null],["amd-radeon-rx-7900-xt","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,"3",null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-llama3-8b-baseline","rocm","fits","F16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","fits","F16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","fits","F16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-llama3-8b-multiview","rocm","fits","F16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-4b-baseline","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-4b-multiview","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-8b-baseline","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","intent-aware-lfqa-qwen3-8b-multiview","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"8",null],["amd-radeon-rx-7900-xt","ising-calibration-1-35b-a3b","rocm","fits","Q3_K_M",8192,18.15,29696,false,null,null,null],["amd-radeon-rx-7900-xt","ising-calibration-1-5-31b-bf16","rocm","fits","IQ3_XXS",8192,18.62,8192,false,null,null,null],["amd-radeon-rx-7900-xt","januscoder-14b","rocm","fits","Q8_0",8192,17.21,16640,false,null,null,null],["amd-radeon-rx-7900-xt","januscoder-8b","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","januscoderv-7b","rocm","fits","BF16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","kanana-2-3b-base","rocm","fits","Q6_K",8192,4.89,32768,false,null,null,null],["amd-radeon-rx-7900-xt","kanana-2-3b-instruct","rocm","fits","F16",8192,8.57,32768,false,null,null,null],["amd-radeon-rx-7900-xt","kat-coder-v2-5-dev","rocm","fits","Q3_K_M",8192,17.62,53504,false,null,null,null],["amd-radeon-rx-7900-xt","kat-dev-72b-exp","rocm","no","IQ2_XXS",8192,28.54,null,null,null,"2",null],["amd-radeon-rx-7900-xt","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-rx-7900-xt","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-rx-7900-xt","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-rx-7900-xt","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-rx-7900-xt","kimi-linear-48b-a3b-base","rocm","fits","IQ2_M",8192,17.24,148224,false,null,null,null],["amd-radeon-rx-7900-xt","kimi-linear-48b-a3b-instruct","rocm","fits","IQ2_M",8192,16.9,181760,false,null,null,null],["amd-radeon-rx-7900-xt","kimi-linear-reap-35b-a3b-instruct","rocm","fits","Q3_K_M",8192,17.93,78336,false,null,null,null],["amd-radeon-rx-7900-xt","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","laguna-xs-2-1","rocm","fits","Q3_K_M",8192,17.1,44288,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-2-6b-exp","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-2-6b-longevity","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-2-6b-transcript","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-24b-a2b","rocm","fits","Q5_K_M",8192,18.03,35072,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-1-2b-base","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-1-2b-instruct","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-1-2b-jp","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-1-2b-jp-202606","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-1-2b-thinking","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-2-6b","rocm","fits","BF16",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-2-6b-base","rocm","fits","Q6_K",8192,3.58,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-230m","rocm","fits","BF16",8192,1.83,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-24b-a2b","rocm","fits","Q5_K_M",8192,18.13,30464,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-350m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-8b-a1b","rocm","fits","BF16",8192,17.99,53504,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-encoder-350m-diffusion","rocm","fits","Q6_K",8192,1.66,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-vl-1-6b","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-vl-1-6b-extract","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-vl-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-vl-450m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-5-vl-450m-extract","rocm","fits","F16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-8b-a1b","rocm","fits","F16",8192,17.73,71424,false,null,null,null],["amd-radeon-rx-7900-xt","lfm2-vl-3b","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xt","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-rx-7900-xt","llama-3-1-70b-instruct","rocm","tight","IQ2_XXS",8192,22.29,null,null,null,null,null],["amd-radeon-rx-7900-xt","llama-3-1-8b-instruct","rocm","fits","BF16",8192,17.05,20224,false,null,null,null],["amd-radeon-rx-7900-xt","llama-3-2-1b-instruct","rocm","fits","BF16",8192,3.97,131072,false,null,null,null],["amd-radeon-rx-7900-xt","llama-3-2-3b-instruct","rocm","fits","BF16",8192,8.5,96512,false,null,null,null],["amd-radeon-rx-7900-xt","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,"2",null],["amd-radeon-rx-7900-xt","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,"3",null],["amd-radeon-rx-7900-xt","mathform-8b","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","medgemma-1-5-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-1-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-12b-a2-5b-base","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-12b-a2-5b-instruct","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-12b-a2-5b-instruct-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mellum2-12b-a2-5b-thinking-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xt","mimo-embodied-7b","rocm","fits","Q6_K",8192,8.14,79616,false,null,null,null],["amd-radeon-rx-7900-xt","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"6",null],["amd-radeon-rx-7900-xt","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-rx-7900-xt","mimo-v2-6-distill-qwen-9b","rocm","fits","BF16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"8",null],["amd-radeon-rx-7900-xt","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"8",null],["amd-radeon-rx-7900-xt","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-xt","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-xt","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"8",null],["amd-radeon-rx-7900-xt","minicpm-o-4-5","rocm","fits","F16",8192,17.34,16896,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm-v-4-6","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm-v-4-6-thinking","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm-v-4-7-1b","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm-v-4-7-35b-a3b","rocm","tight","Q4_K_M",8192,22.4,null,null,null,null,null],["amd-radeon-rx-7900-xt","minicpm5-1b","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm5-1b-base","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm5-1b-sft","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm5-2b","rocm","fits","BF16",8192,6.04,131072,false,null,null,null],["amd-radeon-rx-7900-xt","minicpm5-2b-base","rocm","fits","Q6_K",8192,3.43,262144,true,null,null,null],["amd-radeon-rx-7900-xt","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"6",null],["amd-radeon-rx-7900-xt","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"6",null],["amd-radeon-rx-7900-xt","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"6",null],["amd-radeon-rx-7900-xt","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,"3",null],["amd-radeon-rx-7900-xt","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,"4",null],["amd-radeon-rx-7900-xt","ministral-3-14b-instruct-2512","rocm","fits","Q8_0",8192,15.97,24320,false,null,null,null],["amd-radeon-rx-7900-xt","ministral-3-14b-reasoning-2512","rocm","fits","Q8_0",8192,15.97,24320,false,null,null,null],["amd-radeon-rx-7900-xt","ministral-3-3b-instruct-2512","rocm","fits","BF16",8192,8.86,99840,false,null,null,null],["amd-radeon-rx-7900-xt","ministral-3-3b-reasoning-2512","rocm","fits","BF16",8192,8.86,99840,false,null,null,null],["amd-radeon-rx-7900-xt","ministral-3-8b-instruct-2512","rocm","fits","BF16",8192,17.99,12544,false,null,null,null],["amd-radeon-rx-7900-xt","ministral-3-8b-reasoning-2512","rocm","fits","BF16",8192,17.99,12544,false,null,null,null],["amd-radeon-rx-7900-xt","mistral-7b-instruct-v0-2","rocm","fits","Q6_K",8192,8.05,32768,false,null,null,null],["amd-radeon-rx-7900-xt","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-rx-7900-xt","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,"3",null],["amd-radeon-rx-7900-xt","mistral-nemo-instruct-2407","rocm","fits","Q8_0",8192,14.65,32512,false,null,null,null],["amd-radeon-rx-7900-xt","mistral-small-3-2-24b-instruct-2506","rocm","fits","Q5_K_M",8192,18.57,8448,false,null,null,null],["amd-radeon-rx-7900-xt","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,"3",null],["amd-radeon-rx-7900-xt","muse-glimmer-30b","rocm","fits","Q4_K_M",8192,18.08,43008,false,null,null,null],["amd-radeon-rx-7900-xt","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-rx-7900-xt","nemotron-3-content-safety","rocm","fits","Q6_K",8192,5.37,131072,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","tight","Q4_K_M",8192,23.26,null,null,null,null,null],["amd-radeon-rx-7900-xt","nemotron-cascade-14b-thinking","rocm","fits","Q8_0",8192,17.21,16640,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-cascade-2-30b-a3b","rocm","tight","Q4_0",8192,19.24,null,null,null,null,null],["amd-radeon-rx-7900-xt","nemotron-cascade-8b","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-cascade-8b-thinking","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-orchestrator-8b","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-terminal-14b","rocm","fits","Q6_K",8192,13.89,37120,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-terminal-32b","rocm","fits","IQ3_XXS",8192,15.66,19456,false,null,null,null],["amd-radeon-rx-7900-xt","nemotron-terminal-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xt","north-mini-code-1-0","rocm","fits","IQ4_XS",8192,18.61,8192,false,null,null,null],["amd-radeon-rx-7900-xt","nouscoder-14b","rocm","fits","Q8_0",8192,17.21,16640,false,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.27,null,null,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,"5",null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.18,null,null,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-nano-4b-bf16","rocm","fits","BF16",8192,8.73,262144,false,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,"3",null],["amd-radeon-rx-7900-xt","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,"3",null],["amd-radeon-rx-7900-xt","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","tight","Q4_0",8192,19.03,null,null,null,null,null],["amd-radeon-rx-7900-xt","nvidia-nemotron-nano-9b-v2","rocm","fits","BF16",8192,18.26,28160,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1-32b-instruct","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1-32b-instruct-dpo","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1-32b-think","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1-7b-rl-zero-math","rocm","fits","Q8_0",8192,12.68,27648,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-1125-32b","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-32b-think","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-32b-think-dpo","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-32b-think-sft","rocm","fits","Q3_K_M",8192,18.48,8704,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-instruct","rocm","fits","Q8_0",8192,12.68,27648,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-instruct-dpo","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-instruct-sft","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-rl-zero-general","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-rl-zero-if","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-rl-zero-math","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-rl-zero-mix","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-think","rocm","fits","Q8_0",8192,12.68,27648,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-think-dpo","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmo-3-7b-think-sft","rocm","fits","Q6_K",8192,11.05,40192,false,null,null,null],["amd-radeon-rx-7900-xt","olmocr-2-7b-1025","rocm","fits","BF16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","optimind-sft","rocm","fits","Q5_K_M",8192,17.77,40960,false,null,null,null],["amd-radeon-rx-7900-xt","phi-3-5-mini-instruct","rocm","fits","Q8_0",8192,8.32,34560,false,null,null,null],["amd-radeon-rx-7900-xt","phi-4","rocm","fits","Q8_0",8192,17.66,12800,false,null,null,null],["amd-radeon-rx-7900-xt","phi-4-mini-instruct","rocm","fits","BF16",8192,9.99,74240,false,null,null,null],["amd-radeon-rx-7900-xt","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,"3",null],["amd-radeon-rx-7900-xt","qwen2-5-14b-instruct","rocm","fits","Q8_0",8192,17.48,14080,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-32b-instruct","rocm","fits","Q2_K",8192,15.24,21248,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-3b-instruct","rocm","fits","Q8_0",8192,4.83,32768,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,"2",null],["amd-radeon-rx-7900-xt","qwen2-5-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-coder-32b-instruct","rocm","fits","Q2_K",8192,15.24,21248,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-coder-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-vl-7b-instruct","rocm","fits","BF16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","qwen2-5-vl-7b-surg-cholect50","rocm","fits","F16",8192,15.65,59136,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-0-6b","rocm","fits","BF16",8192,3.41,40960,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-1-7b","rocm","fits","BF16",8192,5.62,40960,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-14b","rocm","fits","Q8_0",8192,17.21,16640,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"6",null],["amd-radeon-rx-7900-xt","qwen3-30b-a3b","rocm","tight","Q5_K_M",8192,23.19,null,null,null,null,null],["amd-radeon-rx-7900-xt","qwen3-30b-a3b-instruct-2507","rocm","fits","IQ4_XS",8192,17.99,14592,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-32b","rocm","tight","Q4_K_M",8192,22.37,null,null,null,null,null],["amd-radeon-rx-7900-xt","qwen3-4b","rocm","fits","Q8_0",8192,6.7,40960,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-4b-instruct-2507","rocm","fits","F16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-0-8b","rocm","fits","BF16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-0-8b-base","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,"3",null],["amd-radeon-rx-7900-xt","qwen3-5-27b","rocm","fits","Q4_K_M",8192,18.36,12032,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-2b","rocm","fits","BF16",8192,5.38,262144,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-2b-base","rocm","fits","Q6_K",8192,3.21,262144,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-35b-a3b","rocm","fits","Q3_K_M",8192,17.55,56576,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-35b-a3b-base","rocm","fits","Q3_K_M",8192,18.14,29952,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","qwen3-5-4b","rocm","fits","BF16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-4b-base","rocm","fits","F16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-9b","rocm","fits","BF16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-5-9b-base","rocm","fits","F16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-6-27b","rocm","fits","Q4_K_M",8192,18.43,11008,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-6-35b-a3b","rocm","fits","Q3_K_M",8192,17.61,53760,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-rx-7900-xt","qwen3-8-27b","rocm","fits","Q4_0",8192,17.74,21504,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-8-3-6-27b-blend","rocm","fits","Q4_0",8192,17.74,21504,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-8b","rocm","fits","Q8_0",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-coder-30b-a3b-instruct","rocm","fits","IQ4_XS",8192,17.99,14592,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xt","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,"2",null],["amd-radeon-rx-7900-xt","qwen3-coder-next-base","rocm","tight","IQ2_XXS",8192,22.32,null,null,null,null,null],["amd-radeon-rx-7900-xt","qwen3-coder-reap-25b-a3b","rocm","fits","Q4_K_M",8192,16.83,26368,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"8",null],["amd-radeon-rx-7900-xt","qwen3-nemotron-14b-brrm","rocm","fits","Q6_K",8192,13.89,37120,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["amd-radeon-rx-7900-xt","qwen3-nemotron-8b-brrm","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,"2",null],["amd-radeon-rx-7900-xt","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"6",null],["amd-radeon-rx-7900-xt","qwen3-vl-2b-instruct","rocm","fits","BF16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-2b-thinking","rocm","fits","BF16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-30b-a3b-instruct","rocm","fits","IQ4_XS",8192,17.99,14592,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-32b-instruct","rocm","fits","Q2_K",8192,15.27,20992,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-32b-thinking","rocm","fits","Q2_K",8192,15.27,20992,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-4b-instruct","rocm","fits","BF16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-4b-thinking","rocm","fits","BF16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-8b-instruct","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","qwen3-vl-8b-thinking","rocm","fits","BF16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","qwq-32b","rocm","tight","Q4_K_M",8192,22.45,null,null,null,null,null],["amd-radeon-rx-7900-xt","riva-translate-4b-instruct-v1-1","rocm","fits","Q6_K",8192,5.97,8192,false,null,null,null],["amd-radeon-rx-7900-xt","rlvr-8b-0926","rocm","fits","Q6_K",8192,8.59,76544,false,null,null,null],["amd-radeon-rx-7900-xt","rnj-1-instruct","rocm","fits","Q8_0",8192,10.99,32768,false,null,null,null],["amd-radeon-rx-7900-xt","sera-32b","rocm","fits","IQ3_XXS",8192,15.66,19456,false,null,null,null],["amd-radeon-rx-7900-xt","singguard-2b","rocm","fits","F16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","smollm3-3b","rocm","fits","BF16",8192,7.9,65536,false,null,null,null],["amd-radeon-rx-7900-xt","smollm3-3b-gsm8k-sft","rocm","fits","Q6_K",8192,4.35,65536,false,null,null,null],["amd-radeon-rx-7900-xt","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,"2",null],["amd-radeon-rx-7900-xt","spatial-ssrl-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xt","spatial-ssrl-qwen3vl-4b","rocm","fits","F16",8192,10.39,64256,false,null,null,null],["amd-radeon-rx-7900-xt","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,"3",null],["amd-radeon-rx-7900-xt","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,"2",null],["amd-radeon-rx-7900-xt","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,"3",null],["amd-radeon-rx-7900-xt","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"5",null],["amd-radeon-rx-7900-xt","step3-vl-10b-base","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xt","tiny-aya-earth","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xt","tiny-aya-fire","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xt","tiny-aya-global","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xt","tiny-aya-water","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xt","translategemma-12b-it","rocm","fits","Q8_0",8192,15.82,50432,false,null,null,null],["amd-radeon-rx-7900-xt","translategemma-27b-it","rocm","fits","Q3_K_M",8192,17.3,24064,false,null,null,null],["amd-radeon-rx-7900-xt","translategemma-4b-it","rocm","fits","F16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"7",null],["amd-radeon-rx-7900-xt","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"8",null],["amd-radeon-rx-7900-xt","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"7",null],["amd-radeon-rx-7900-xt","trinity-mini","rocm","fits","Q4_K_M",8192,17.35,77056,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-mini-base","rocm","fits","Q4_K_M",8192,17.24,83200,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-mini-base-pre-anneal","rocm","fits","Q4_K_M",4096,16.96,4096,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-nano-base","rocm","fits","Q6_K",8192,6.67,131072,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-nano-base-pre-anneal","rocm","fits","Q6_K",4096,6.43,4096,false,null,null,null],["amd-radeon-rx-7900-xt","trinity-nano-preview","rocm","fits","BF16",8192,13.51,131072,false,null,null,null],["amd-radeon-rx-7900-xt","ui-mate-27b","rocm","fits","Q4_0",8192,17.74,21504,false,null,null,null],["amd-radeon-rx-7900-xt","ui-mate-9b","rocm","fits","BF16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","ui-mate-democua-27b","rocm","fits","Q4_K_M",8192,18.17,15104,false,null,null,null],["amd-radeon-rx-7900-xt","ui-venus-1-5-2b","rocm","fits","F16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","ui-venus-1-5-30b-a3b","rocm","fits","IQ4_XS",8192,18.17,12544,false,null,null,null],["amd-radeon-rx-7900-xt","ui-venus-1-5-8b","rocm","fits","Q6_K",8192,8.59,76544,false,null,null,null],["amd-radeon-rx-7900-xt","ui-venus-2-9b","rocm","fits","BF16",8192,17.55,39680,false,null,null,null],["amd-radeon-rx-7900-xt","userrepgen-4b","rocm","fits","BF16",8192,10.23,253952,false,null,null,null],["amd-radeon-rx-7900-xt","webworld-14b","rocm","fits","Q6_K",8192,13.89,37120,false,null,null,null],["amd-radeon-rx-7900-xt","webworld-32b","rocm","fits","IQ3_XXS",8192,15.66,19456,false,null,null,null],["amd-radeon-rx-7900-xt","webworld-8b","rocm","fits","F16",8192,17.35,16896,false,null,null,null],["amd-radeon-rx-7900-xt","x-reasoner-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xt","youtu-llm-2b","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-xt","youtu-llm-2b-base","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-xt","youtu-vl-4b-instruct","rocm","fits","Q6_K",8192,5.91,32768,false,null,null,null],["amd-radeon-rx-7900-xt","zwz-2b","rocm","fits","F16",8192,5.62,121856,false,null,null,null],["amd-radeon-rx-7900-xt","zwz-4b","rocm","fits","Q6_K",8192,5.74,96000,false,null,null,null],["amd-radeon-rx-7900-xt","zwz-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xt","zwz-8b","rocm","fits","Q6_K",8192,8.59,76544,false,null,null,null],["amd-radeon-rx-7900-xtx","aescode-32b","rocm","fits","Q4_0",8192,21.67,12288,false,null,null,null],["amd-radeon-rx-7900-xtx","aescode-8b","rocm","fits","BF16",8192,17.35,45056,false,null,null,null],["amd-radeon-rx-7900-xtx","agentcpm-explore","rocm","fits","Q6_K",8192,5.74,124160,false,null,null,null],["amd-radeon-rx-7900-xtx","ai21-jamba-reasoning-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","ai21-jamba2-3b","rocm","fits","BF16",8192,7.27,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","ai21-jamba2-mini","rocm","fits","IQ3_XXS",8192,21.21,93440,false,null,null,null],["amd-radeon-rx-7900-xtx","apertus-v1-1-1-5b","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-xtx","apertus-v1-1-1-5b-instruct","rocm","fits","F16",4096,3.84,4096,false,null,null,null],["amd-radeon-rx-7900-xtx","apertus-v1-1-4b","rocm","fits","Q6_K",4096,4.42,4096,false,null,null,null],["amd-radeon-rx-7900-xtx","apriel-1-6-15b-thinker","rocm","fits","Q8_0",8192,17.19,36608,false,null,null,null],["amd-radeon-rx-7900-xtx","aprielguard","rocm","fits","Q6_K",8192,7.87,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","armorocr","rocm","fits","Q8_0",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","astabrief-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","autoglm-phone-9b","rocm","fits","F16",8192,18.87,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","autoglm-phone-9b-multilingual","rocm","fits","Q6_K",8192,9.25,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","baichuan-m3-235b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","beam-1-0-501b-a23b","rocm","no","Q8_0",8192,523.57,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","bielik-11b-v3-0-instruct","rocm","fits","Q8_0",8192,14.42,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","bielik-minitron-7b-v3-0-instruct","rocm","fits","Q8_0",8192,10.25,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","bitcpm-cann-3b-unquantized","rocm","fits","Q6_K",8192,4.29,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","caprl-qwen3vl-2b","rocm","fits","F16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","caprl-qwen3vl-4b","rocm","fits","F16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","cogito-671b-v2-1","rocm","no","Q2_K",8192,242.4,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","command-a-plus-05-2026-bf16","rocm","no","IQ2_XXS",8192,63.63,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","contextpilot-14b","rocm","fits","Q8_0",8192,17.21,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","contextpilot-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","contextpilot-e4b","rocm","fits","F16",8192,10.89,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","cosmos-reason2-32b","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","cosmos-reason2-8b","rocm","fits","Q6_K",8192,8.59,104704,false,null,null,null],["amd-radeon-rx-7900-xtx","d1-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-r1","rocm","no","Q2_K",8192,280.34,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","deepseek-r1-0528-qwen3-8b","rocm","fits","BF16",8192,17.35,45056,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-r1-distill-llama-70b","rocm","no","Q2_K",8192,29.42,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","deepseek-r1-distill-llama-8b","rocm","fits","BF16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-r1-distill-qwen-14b","rocm","fits","Q8_0",8192,17.48,35072,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-r1-distill-qwen-32b","rocm","fits","Q4_K_M",8192,22.45,9216,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-r1-distill-qwen-7b","rocm","fits","F16",8192,15.65,130048,false,null,null,null],["amd-radeon-rx-7900-xtx","deepseek-v3","rocm","no","Q2_K",8192,257.8,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","deepseek-v3-1","rocm","no","Q2_K",8192,242.41,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","deepseek-v3-2","rocm","no","Q2_K",8192,242.08,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","devstral-2-123b-instruct-2512","rocm","no","Q2_K",8192,49.32,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","devstral-small-2-24b-instruct-2512","rocm","fits","Q6_K",8192,21.01,18688,false,null,null,null],["amd-radeon-rx-7900-xtx","eurollm-22b-2512","rocm","fits","Q6_K",8192,20.63,17664,false,null,null,null],["amd-radeon-rx-7900-xtx","eurollm-22b-instruct-2512","rocm","fits","Q6_K",8192,20.63,17664,false,null,null,null],["amd-radeon-rx-7900-xtx","eurollm-9b-instruct-2512","rocm","fits","F16",8192,19.58,26624,false,null,null,null],["amd-radeon-rx-7900-xtx","euromoe-2-6b-a0-6b-instruct-2512","rocm","fits","Q6_K",8192,3.58,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","exaone-4-5-33b","rocm","fits","Q4_K_M",8192,22.33,9728,false,null,null,null],["amd-radeon-rx-7900-xtx","fara-7b","rocm","fits","BF16",8192,15.65,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","fara1-5-27b","rocm","fits","Q5_K_M",8192,21.9,20992,false,null,null,null],["amd-radeon-rx-7900-xtx","fara1-5-4b","rocm","fits","BF16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","fara1-5-9b","rocm","fits","BF16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","frogboss-32b-2510","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","frogmini-14b-2510","rocm","fits","Q6_K",8192,13.89,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","frognano-4b-2609","rocm","fits","BF16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","functiongemma-270m-it","rocm","fits","BF16",8192,2.14,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","gelab-zero-4b-preview","rocm","fits","BF16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-2-27b-it","rocm","fits","Q4_K_M",8192,20.89,8192,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-2-9b-it","rocm","fits","Q8_0",8192,14.78,8192,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-3-12b-it","rocm","fits","Q8_0",8192,15.82,112640,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-3-1b-it","rocm","fits","BF16",8192,3.6,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-3-27b-it","rocm","fits","Q4_K_M",8192,20.35,37120,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-3-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-12b","rocm","fits","Q8_0",8192,15.57,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-12b-it","rocm","fits","Q8_0",8192,15.57,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-26b-a4b","rocm","fits","Q5_K_M",8192,21.38,69888,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-26b-a4b-it","rocm","fits","Q5_K_M",8192,21.57,61696,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-31b","rocm","fits","IQ4_XS",8192,22.43,12032,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-31b-it","rocm","fits","IQ4_XS",8192,21.95,17920,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-e2b","rocm","fits","Q6_K",8192,3.49,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-e2b-it","rocm","fits","BF16",8192,6.14,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-e4b","rocm","fits","F16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","gemma-4-e4b-it","rocm","fits","BF16",8192,11,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","glm-4-5","rocm","no","Q2_K",8192,130.74,null,null,null,"7",null],["amd-radeon-rx-7900-xtx","glm-4-5-air","rocm","no","Q2_K",8192,45.62,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","glm-4-5-air-reap-82b-a12b","rocm","no","IQ2_XXS",8192,31.08,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","glm-4-6-reap-268b-a32b","rocm","no","Q2_K",8192,100.87,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","glm-4-6v","rocm","no","Q2_K",8192,45.62,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","glm-4-6v-flash","rocm","fits","BF16",8192,18.87,100096,false,null,null,null],["amd-radeon-rx-7900-xtx","glm-4-7","rocm","no","Q2_K",8192,130.74,null,null,null,"7",null],["amd-radeon-rx-7900-xtx","glm-4-7-flash","rocm","fits","Q5_K_M",8192,22.53,12032,false,null,null,null],["amd-radeon-rx-7900-xtx","glm-4-7-flash-reap-23b-a3b","rocm","fits","Q6_K",8192,20.11,55808,false,null,null,null],["amd-radeon-rx-7900-xtx","glm-4-7-reap-218b-a32b","rocm","no","Q2_K",8192,82.94,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","glm-4-7-reap-268b-a32b","rocm","no","IQ2_XXS",8192,73.04,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","glm-5","rocm","no","Q2_K",8192,268.86,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","glm-5-1","rocm","no","IQ2_XXS",8192,197.58,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xtx","glm-5-2","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","glm-5-3","rocm","no","Q8_0",8192,776.44,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","glm-5-3-flash","rocm","no","Q8_0",8192,327.9,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","glm-5-3-flash-bf16","rocm","no","IQ2_XXS",8192,91.96,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","gpt-oss-120b","rocm","no","Q2_K",8192,62.76,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","gpt-oss-20b","rocm","fits","Q8_0",8192,12.9,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-3-3-8b-instruct","rocm","fits","F16",8192,18.62,33536,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-0-1b","rocm","fits","BF16",8192,5.14,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-0-350m","rocm","fits","BF16",8192,2.2,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-0-h-1b","rocm","fits","BF16",8192,4.44,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-0-h-350m","rocm","fits","BF16",8192,2.07,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-1-30b","rocm","fits","Q4_K_M",8192,20.53,16640,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-1-3b","rocm","fits","BF16",8192,8.61,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-1-8b","rocm","fits","BF16",8192,19.03,30976,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-2-30b","rocm","fits","Q4_K_M",8192,20.53,16640,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-2-3b","rocm","fits","BF16",8192,8.61,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-4-2-8b","rocm","fits","BF16",8192,19.03,30976,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-guardian-3-2-8b-factuality-detection","rocm","fits","F16",8192,18.62,33536,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-guardian-4-0-3b-toxicity-ja","rocm","fits","Q6_K",8192,4.67,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-guardian-4-1-8b","rocm","fits","BF16",8192,19.03,30976,false,null,null,null],["amd-radeon-rx-7900-xtx","granite-vision-4-1-4b","rocm","fits","BF16",8192,8.61,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","harc-llama-3-1-8b-instruct","rocm","fits","Q6_K",8192,8.37,118272,false,null,null,null],["amd-radeon-rx-7900-xtx","harc-qwen2-5-7b-instruct","rocm","fits","Q6_K",8192,7.47,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","hermes-4-3-36b","rocm","fits","IQ4_XS",8192,22.13,10496,false,null,null,null],["amd-radeon-rx-7900-xtx","hipo-1-7b","rocm","fits","Q6_K",8192,3.63,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","holo-3-1-0-8b","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","holo-3-1-35b-a3b","rocm","fits","Q4_K_M",8192,22.4,24064,false,null,null,null],["amd-radeon-rx-7900-xtx","holo-3-1-4b","rocm","fits","F16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","holo-3-1-9b","rocm","fits","F16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","holo2-235b-a22b","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","holo2-30b-a3b","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","holo2-4b","rocm","fits","F16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","holo2-8b","rocm","fits","Q6_K",8192,8.59,104704,false,null,null,null],["amd-radeon-rx-7900-xtx","holo3-35b-a3b","rocm","fits","Q4_K_M",8192,22.4,24064,false,null,null,null],["amd-radeon-rx-7900-xtx","holo4-27b","rocm","fits","Q5_K_M",8192,20.64,39936,false,null,null,null],["amd-radeon-rx-7900-xtx","holo4-35b-a3b","rocm","fits","Q4_0",8192,21.2,78336,false,null,null,null],["amd-radeon-rx-7900-xtx","holotron4-30b-a3b","rocm","fits","Q4_0",8192,19.03,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","hunyuanocr","rocm","fits","F16",8192,3.13,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","hy3","rocm","no","IQ2_XXS",8192,82.17,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","intellect-3","rocm","no","IQ2_XXS",8192,39.58,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-llama3-8b-baseline","rocm","fits","F16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-llama3-8b-intent-explicit","rocm","fits","F16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-llama3-8b-intent-implicit","rocm","fits","F16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-llama3-8b-multiview","rocm","fits","F16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-4b-baseline","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-4b-intent-explicit","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-4b-intent-implicit","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-4b-multiview","rocm","fits","F16",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-8b-baseline","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-8b-intent-explicit","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-8b-intent-implicit","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intent-aware-lfqa-qwen3-8b-multiview","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","intern-s2-397b","rocm","no","IQ2_XXS",8192,114.31,null,null,null,"7",null],["amd-radeon-rx-7900-xtx","ising-calibration-1-35b-a3b","rocm","fits","Q4_K_M",8192,22.4,24064,false,null,null,null],["amd-radeon-rx-7900-xtx","ising-calibration-1-5-31b-bf16","rocm","fits","IQ4_XS",8192,22.71,8448,false,null,null,null],["amd-radeon-rx-7900-xtx","januscoder-14b","rocm","fits","Q8_0",8192,17.21,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","januscoder-8b","rocm","fits","BF16",8192,17.35,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","januscoderv-7b","rocm","fits","BF16",8192,15.65,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","k-exaone-236b-a23b","rocm","no","IQ4_XS",8192,126.29,null,null,null,"7",null],["amd-radeon-rx-7900-xtx","kanana-2-3b-base","rocm","fits","Q6_K",8192,4.89,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","kanana-2-3b-instruct","rocm","fits","F16",8192,8.57,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","kat-coder-v2-5-dev","rocm","fits","Q4_K_M",8192,22.62,14080,false,null,null,null],["amd-radeon-rx-7900-xtx","kat-dev-72b-exp","rocm","tight","IQ2_XXS",8192,28.54,null,null,null,null,null],["amd-radeon-rx-7900-xtx","kimi-k2-5","rocm","no","Q2_K",8192,367.95,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","kimi-k2-6","rocm","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","kimi-k2-instruct","rocm","no","Q2_K",8192,367.37,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","kimi-k2-thinking","rocm","no","Q2_K",8192,368.29,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","kimi-linear-48b-a3b-base","rocm","fits","IQ3_XXS",8192,20.04,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","kimi-linear-48b-a3b-instruct","rocm","fits","IQ3_XXS",8192,20.69,216320,false,null,null,null],["amd-radeon-rx-7900-xtx","kimi-linear-reap-35b-a3b-instruct","rocm","fits","Q4_K_M",8192,22.22,61952,false,null,null,null],["amd-radeon-rx-7900-xtx","laguna-s-2-1","rocm","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xtx","laguna-xs-2-1","rocm","fits","Q4_K_M",8192,21.95,27136,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-2-6b-exp","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-2-6b-longevity","rocm","fits","F16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-2-6b-transcript","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-24b-a2b","rocm","fits","Q6_K",8192,20.64,103680,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-1-2b-base","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-1-2b-instruct","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-1-2b-jp","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-1-2b-jp-202606","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-1-2b-thinking","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-2-6b","rocm","fits","BF16",8192,6.7,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-2-6b-base","rocm","fits","Q6_K",8192,3.58,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-230m","rocm","fits","BF16",8192,1.83,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-24b-a2b","rocm","fits","Q6_K",8192,20.74,99072,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-350m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-8b-a1b","rocm","fits","BF16",8192,17.99,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-encoder-350m-diffusion","rocm","fits","Q6_K",8192,1.66,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-vl-1-6b","rocm","fits","BF16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-vl-1-6b-extract","rocm","fits","F16",8192,3.67,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-vl-3b","rocm","fits","BF16",8192,6.7,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-vl-450m","rocm","fits","BF16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-5-vl-450m-extract","rocm","fits","F16",8192,2.07,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-8b-a1b","rocm","fits","F16",8192,17.73,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","lfm2-vl-3b","rocm","fits","BF16",8192,6.45,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","ling-1t","rocm","no","Q2_K",8192,360.62,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","llama-3-1-70b-instruct","rocm","fits","IQ2_XXS",8192,22.29,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","llama-3-1-8b-instruct","rocm","fits","BF16",8192,17.05,51712,false,null,null,null],["amd-radeon-rx-7900-xtx","llama-3-2-1b-instruct","rocm","fits","BF16",8192,3.97,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","llama-3-2-3b-instruct","rocm","fits","BF16",8192,8.5,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","llama-3-3-70b-instruct","rocm","no","Q2_K",8192,29.42,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","llama-4-scout-17b-16e-instruct","rocm","no","Q2_K",8192,41.46,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","mathform-8b","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","medgemma-1-5-4b-it","rocm","fits","BF16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-1-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-12b-a2-5b-base","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-12b-a2-5b-instruct","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-12b-a2-5b-instruct-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-12b-a2-5b-thinking","rocm","fits","Q8_0",8192,14.03,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mellum2-12b-a2-5b-thinking-sft","rocm","fits","Q6_K",8192,12.08,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","mimo-embodied-7b","rocm","fits","Q6_K",8192,8.14,107776,false,null,null,null],["amd-radeon-rx-7900-xtx","mimo-v2-5","rocm","no","IQ2_XXS",8192,82.44,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","mimo-v2-5-pro","rocm","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","mimo-v2-6-distill-qwen-9b","rocm","fits","BF16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","mimo-v2-6-flash-mopd","rocm","no","Q2_K",8192,124.94,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","mimo-v2-6-flash-rl","rocm","no","Q2_K",8192,124.94,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","mimo-v2-6-pro-mopd","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","mimo-v2-6-pro-rl","rocm","no","Q2_K",8192,411.6,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","mimo-v2-flash","rocm","no","Q2_K",8192,111.57,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","minicpm-o-4-5","rocm","fits","F16",8192,17.34,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm-v-4-6","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm-v-4-6-thinking","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm-v-4-7-1b","rocm","fits","F16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm-v-4-7-35b-a3b","rocm","fits","Q4_K_M",8192,22.4,24064,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm5-1b","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm5-1b-base","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm5-1b-sft","rocm","fits","Q6_K",8192,2.18,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm5-2b","rocm","fits","BF16",8192,6.04,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","minicpm5-2b-base","rocm","fits","Q6_K",8192,3.43,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","minimax-m2","rocm","no","Q2_K",8192,84.92,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","minimax-m2-1","rocm","no","Q2_K",8192,84.92,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","minimax-m2-5","rocm","no","Q2_K",8192,84.92,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","minimax-m2-5-reap-139b-a10b","rocm","no","IQ2_XXS",8192,39.25,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","minimax-m2-7","rocm","no","IQ2_XXS",8192,62.9,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","ministral-3-14b-instruct-2512","rocm","fits","Q8_0",8192,15.97,49664,false,null,null,null],["amd-radeon-rx-7900-xtx","ministral-3-14b-reasoning-2512","rocm","fits","Q8_0",8192,15.97,49664,false,null,null,null],["amd-radeon-rx-7900-xtx","ministral-3-3b-instruct-2512","rocm","fits","BF16",8192,8.86,138496,false,null,null,null],["amd-radeon-rx-7900-xtx","ministral-3-3b-reasoning-2512","rocm","fits","BF16",8192,8.86,138496,false,null,null,null],["amd-radeon-rx-7900-xtx","ministral-3-8b-instruct-2512","rocm","fits","BF16",8192,17.99,42496,false,null,null,null],["amd-radeon-rx-7900-xtx","ministral-3-8b-reasoning-2512","rocm","fits","BF16",8192,17.99,42496,false,null,null,null],["amd-radeon-rx-7900-xtx","mistral-7b-instruct-v0-2","rocm","fits","Q6_K",8192,8.05,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","mistral-large-3-675b-instruct-2512","rocm","no","Q2_K",8192,243.79,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","mistral-medium-3-5-128b","rocm","no","Q2_K",8192,49.32,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","mistral-nemo-instruct-2407","rocm","fits","Q8_0",8192,14.65,57856,false,null,null,null],["amd-radeon-rx-7900-xtx","mistral-small-3-2-24b-instruct-2506","rocm","fits","Q6_K",8192,21.01,18688,false,null,null,null],["amd-radeon-rx-7900-xtx","mistral-small-4-119b-2603","rocm","no","IQ2_XXS",8192,34.29,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","muse-glimmer-30b","rocm","fits","Q5_K_M",8192,20.66,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","muse-spark-open-816b-a42b","rocm","no","Q2_K",8192,301.03,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","nemotron-3-content-safety","rocm","fits","Q6_K",8192,5.37,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","rocm","tight","Q4_K_M",8192,23.26,null,null,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-cascade-14b-thinking","rocm","fits","Q8_0",8192,17.21,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-cascade-2-30b-a3b","rocm","fits","Q4_0",8192,19.24,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-cascade-8b","rocm","fits","BF16",8192,17.35,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-cascade-8b-thinking","rocm","fits","BF16",8192,17.35,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-orchestrator-8b","rocm","fits","BF16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-terminal-14b","rocm","fits","Q6_K",8192,13.89,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-terminal-32b","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","nemotron-terminal-8b","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","north-mini-code-1-0","rocm","fits","Q4_K_M",8192,20.73,56832,false,null,null,null],["amd-radeon-rx-7900-xtx","nouscoder-14b","rocm","fits","Q8_0",8192,17.21,42240,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","rocm","fits","Q4_0",8192,19.03,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","rocm","fits","Q4_0",8192,19.27,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","rocm","no","Q4_0",8192,71.85,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-nano-30b-a3b-bf16","rocm","fits","Q4_0",8192,19.18,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-nano-4b-bf16","rocm","fits","BF16",8192,8.73,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-super-120b-a12b-base-bf16","rocm","no","IQ2_XXS",8192,49.78,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-3-super-120b-a12b-bf16","rocm","no","IQ2_XXS",8192,51.01,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","rocm","fits","Q4_0",8192,19.03,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","nvidia-nemotron-nano-9b-v2","rocm","fits","BF16",8192,18.26,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1-32b-instruct","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1-32b-instruct-dpo","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1-32b-think","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1-7b-rl-zero-math","rocm","fits","F16",8192,19.01,15360,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-1125-32b","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-32b-think","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-32b-think-dpo","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-32b-think-sft","rocm","fits","Q4_K_M",8192,22.21,10240,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-instruct","rocm","fits","BF16",8192,19.01,15360,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-instruct-dpo","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-instruct-sft","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-rl-zero-code","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-rl-zero-general","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-rl-zero-if","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-rl-zero-math","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-rl-zero-mix","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-think","rocm","fits","BF16",8192,19.01,15360,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-think-dpo","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmo-3-7b-think-sft","rocm","fits","Q6_K",8192,11.05,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","olmocr-2-7b-1025","rocm","fits","BF16",8192,15.65,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","optimind-sft","rocm","fits","Q5_K_M",8192,17.77,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","phi-3-5-mini-instruct","rocm","fits","Q8_0",8192,8.32,45312,false,null,null,null],["amd-radeon-rx-7900-xtx","phi-4","rocm","fits","Q8_0",8192,17.66,16384,false,null,null,null],["amd-radeon-rx-7900-xtx","phi-4-mini-instruct","rocm","fits","BF16",8192,9.99,105728,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen-agentworld-35b-a3b","rocm","no","Q8_0",8192,37.57,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","qwen2-5-14b-instruct","rocm","fits","Q8_0",8192,17.48,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-32b-instruct","rocm","fits","Q4_K_M",8192,22.45,9216,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-3b-instruct","rocm","fits","Q8_0",8192,4.83,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-72b-instruct","rocm","no","Q2_K",8192,30.34,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","qwen2-5-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-coder-32b-instruct","rocm","fits","Q4_K_M",8192,22.45,9216,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-coder-7b-instruct","rocm","fits","Q8_0",8192,9.15,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-vl-7b-instruct","rocm","fits","BF16",8192,15.65,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen2-5-vl-7b-surg-cholect50","rocm","fits","F16",8192,15.65,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-0-6b","rocm","fits","BF16",8192,3.41,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-1-7b","rocm","fits","BF16",8192,5.62,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-14b","rocm","fits","Q8_0",8192,17.21,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-235b-a22b","rocm","no","Q4_K_M",8192,141.88,null,null,null,"8",null],["amd-radeon-rx-7900-xtx","qwen3-235b-a22b-instruct-2507","rocm","no","Q2_K",8192,86.67,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","qwen3-30b-a3b","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-30b-a3b-instruct-2507","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-32b","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-4b","rocm","fits","Q8_0",8192,6.7,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-4b-instruct-2507","rocm","fits","F16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-0-8b","rocm","fits","BF16",8192,3.17,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-0-8b-base","rocm","fits","Q6_K",8192,2.3,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-122b-a10b","rocm","no","IQ2_XXS",8192,35.03,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","qwen3-5-27b","rocm","fits","Q5_K_M",8192,21.01,34304,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-2b","rocm","fits","BF16",8192,5.38,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-2b-base","rocm","fits","Q6_K",8192,3.21,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-35b-a3b","rocm","fits","Q3_K_M",8192,17.55,243456,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-35b-a3b-base","rocm","fits","Q4_K_M",8192,22.4,23808,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-397b-a17b","rocm","no","Q3_K_M",8192,175.62,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xtx","qwen3-5-4b","rocm","fits","BF16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-4b-base","rocm","fits","F16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-9b","rocm","fits","BF16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-5-9b-base","rocm","fits","F16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-6-27b","rocm","fits","Q5_K_M",8192,20.92,35840,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-6-35b-a3b","rocm","fits","Q4_K_M",8192,22.61,14336,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-8-2-4t-a95b","rocm","no","Q8_0",8192,2524.12,null,null,null,"over",null],["amd-radeon-rx-7900-xtx","qwen3-8-27b","rocm","fits","Q5_K_M",8192,22.07,18432,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-8-3-6-27b-blend","rocm","fits","Q5_K_M",8192,22.07,18432,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-8b","rocm","fits","Q8_0",8192,10.39,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-coder-30b-a3b-instruct","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-coder-480b-a35b-instruct","rocm","no","Q2_K",8192,174.28,null,null,null,"8:tight",null],["amd-radeon-rx-7900-xtx","qwen3-coder-next","rocm","no","Q2_K",8192,30.37,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","qwen3-coder-next-base","rocm","fits","IQ2_XXS",8192,22.32,24320,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-coder-reap-25b-a3b","rocm","fits","Q6_K",8192,21.9,16640,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-coder-reap-363b-a35b","rocm","no","Q2_K",8192,132.69,null,null,null,"7",null],["amd-radeon-rx-7900-xtx","qwen3-nemotron-14b-brrm","rocm","fits","Q6_K",8192,13.89,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-nemotron-235b-a22b-genrm","rocm","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","qwen3-nemotron-8b-brrm","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-next-80b-a3b-instruct","rocm","no","Q2_K",8192,30.32,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","qwen3-vl-235b-a22b-instruct","rocm","no","Q2_K",8192,86.67,null,null,null,"5",null],["amd-radeon-rx-7900-xtx","qwen3-vl-2b-instruct","rocm","fits","BF16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-2b-thinking","rocm","fits","BF16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-30b-a3b-instruct","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-32b-instruct","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-32b-thinking","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-4b-instruct","rocm","fits","BF16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-4b-thinking","rocm","fits","BF16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-8b-instruct","rocm","fits","BF16",8192,17.35,45056,false,null,null,null],["amd-radeon-rx-7900-xtx","qwen3-vl-8b-thinking","rocm","fits","BF16",8192,17.35,45056,false,null,null,null],["amd-radeon-rx-7900-xtx","qwq-32b","rocm","fits","Q4_K_M",8192,22.45,9216,false,null,null,null],["amd-radeon-rx-7900-xtx","riva-translate-4b-instruct-v1-1","rocm","fits","Q6_K",8192,5.97,8192,false,null,null,null],["amd-radeon-rx-7900-xtx","rlvr-8b-0926","rocm","fits","Q6_K",8192,8.59,104704,false,null,null,null],["amd-radeon-rx-7900-xtx","rnj-1-instruct","rocm","fits","BF16",8192,18.63,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","sera-32b","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","singguard-2b","rocm","fits","F16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","smollm3-3b","rocm","fits","BF16",8192,7.9,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","smollm3-3b-gsm8k-sft","rocm","fits","Q6_K",8192,4.35,65536,false,null,null,null],["amd-radeon-rx-7900-xtx","solar-open-100b","rocm","no","IQ2_XXS",8192,29.36,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","spatial-ssrl-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","spatial-ssrl-qwen3vl-4b","rocm","fits","F16",8192,10.39,92416,false,null,null,null],["amd-radeon-rx-7900-xtx","step-3-5-flash","rocm","no","IQ2_XXS",8192,48.93,null,null,null,"3",null],["amd-radeon-rx-7900-xtx","step-3-5-flash-reap-121b-a11b","rocm","no","IQ2_XXS",8192,32.92,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","step-3-5-flash-reap-149b-a11b","rocm","no","IQ2_XXS",8192,40.14,null,null,null,"2",null],["amd-radeon-rx-7900-xtx","step-3-7-flash","rocm","no","IQ3_XXS",8192,76.06,null,null,null,"4",null],["amd-radeon-rx-7900-xtx","step3-vl-10b-base","rocm","fits","Q6_K",8192,8.59,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","tiny-aya-earth","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","tiny-aya-fire","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","tiny-aya-global","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","tiny-aya-water","rocm","fits","BF16",8192,8.72,262144,true,null,null,null],["amd-radeon-rx-7900-xtx","translategemma-12b-it","rocm","fits","Q8_0",8192,15.82,112640,false,null,null,null],["amd-radeon-rx-7900-xtx","translategemma-27b-it","rocm","fits","Q4_K_M",8192,20.35,37120,false,null,null,null],["amd-radeon-rx-7900-xtx","translategemma-4b-it","rocm","fits","F16",8192,9.86,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-large-base","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","trinity-large-thinking","rocm","no","IQ2_XXS",8192,107.1,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","trinity-large-truebase","rocm","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["amd-radeon-rx-7900-xtx","trinity-mini","rocm","fits","Q6_K",8192,22.72,8448,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-mini-base","rocm","fits","Q6_K",8192,22.67,11264,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-mini-base-pre-anneal","rocm","fits","Q6_K",4096,22.39,4096,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-nano-base","rocm","fits","Q6_K",8192,6.67,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-nano-base-pre-anneal","rocm","fits","Q6_K",4096,6.43,4096,false,null,null,null],["amd-radeon-rx-7900-xtx","trinity-nano-preview","rocm","fits","BF16",8192,13.51,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-mate-27b","rocm","fits","Q5_K_M",8192,21.9,20992,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-mate-9b","rocm","fits","BF16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-mate-democua-27b","rocm","fits","Q5_K_M",8192,20.64,39936,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-venus-1-5-2b","rocm","fits","F16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-venus-1-5-30b-a3b","rocm","fits","Q4_K_M",8192,20.13,34816,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-venus-1-5-8b","rocm","fits","Q6_K",8192,8.59,104704,false,null,null,null],["amd-radeon-rx-7900-xtx","ui-venus-2-9b","rocm","fits","BF16",8192,17.55,160512,false,null,null,null],["amd-radeon-rx-7900-xtx","userrepgen-4b","rocm","fits","BF16",8192,10.23,262144,false,null,null,null],["amd-radeon-rx-7900-xtx","webworld-14b","rocm","fits","Q6_K",8192,13.89,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","webworld-32b","rocm","fits","Q4_K_M",8192,22.37,9472,false,null,null,null],["amd-radeon-rx-7900-xtx","webworld-8b","rocm","fits","F16",8192,17.35,40960,false,null,null,null],["amd-radeon-rx-7900-xtx","x-reasoner-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","youtu-llm-2b","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","youtu-llm-2b-base","rocm","fits","Q6_K",8192,3.16,131072,false,null,null,null],["amd-radeon-rx-7900-xtx","youtu-vl-4b-instruct","rocm","fits","Q6_K",8192,5.91,32768,false,null,null,null],["amd-radeon-rx-7900-xtx","zwz-2b","rocm","fits","F16",8192,5.62,157696,false,null,null,null],["amd-radeon-rx-7900-xtx","zwz-4b","rocm","fits","Q6_K",8192,5.74,124160,false,null,null,null],["amd-radeon-rx-7900-xtx","zwz-7b","rocm","fits","Q6_K",8192,7.47,128000,false,null,null,null],["amd-radeon-rx-7900-xtx","zwz-8b","rocm","fits","Q6_K",8192,8.59,104704,false,null,null,null],["nvidia-b100","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-b100","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-b100","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-b100","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-b100","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-b100","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-b100","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-b100","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-b100","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-b100","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-b100","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b100","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-b100","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-b100","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-b100","baichuan-m3-235b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b100","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,null,null],["nvidia-b100","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-b100","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-b100","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-b100","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-b100","command-a-plus-05-2026-bf16","cuda","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["nvidia-b100","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-b100","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-b100","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b100","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-b100","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b100","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-b100","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-b100","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-b100","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-b100","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-b100","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-b100","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-b100","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-b100","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-b100","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-b100","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b100","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-b100","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-b100","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b100","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b100","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b100","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b100","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-b100","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-b100","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-5","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-6-reap-268b-a32b","cuda","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-7","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-7-reap-218b-a32b","cuda","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-4-7-reap-268b-a32b","cuda","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-b100","glm-5-1","cuda","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["nvidia-b100","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-b100","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-b100","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-b100","glm-5-3-flash-bf16","cuda","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["nvidia-b100","gpt-oss-120b","cuda","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["nvidia-b100","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-b100","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-b100","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-b100","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b100","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-b100","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-b100","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-b100","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-b100","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-b100","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-b100","holo2-235b-a22b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b100","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b100","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-b100","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-b100","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-b100","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b100","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-b100","hy3","cuda","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["nvidia-b100","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","intern-s2-397b","cuda","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["nvidia-b100","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-b100","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-b100","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-b100","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b100","k-exaone-236b-a23b","cuda","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["nvidia-b100","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-b100","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-b100","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-b100","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-b100","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-b100","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-b100","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-b100","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-b100","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-b100","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-b100","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-b100","laguna-s-2-1","cuda","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["nvidia-b100","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-b100","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b100","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-b100","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-b100","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b100","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-b100","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b100","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-b100","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-b100","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-b100","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-v2-5","cuda","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-b100","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-v2-6-flash-mopd","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-v2-6-flash-rl","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-b100","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-b100","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-b100","mimo-v2-flash","cuda","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-b100","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-b100","minimax-m2","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b100","minimax-m2-1","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b100","minimax-m2-5","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b100","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-b100","minimax-m2-7","cuda","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-b100","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-b100","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-b100","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-b100","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-b100","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-b100","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-b100","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-b100","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-b100","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-b100","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b100","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-b100","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b100","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b100","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b100","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-b100","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-b100","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-b100","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-235b-a22b","cuda","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-235b-a22b-instruct-2507","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-397b-a17b","cuda","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-b100","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-480b-a35b-instruct","cuda","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-coder-reap-363b-a35b","cuda","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-nemotron-235b-a22b-genrm","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-235b-a22b-instruct","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-b100","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-b100","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-b100","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b100","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-b100","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-b100","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-b100","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b100","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b100","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-b100","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-b100","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-b100","step-3-7-flash","cuda","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["nvidia-b100","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b100","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b100","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b100","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b100","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-b100","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-b100","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-large-base","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-large-thinking","cuda","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-large-truebase","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-b100","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b100","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b100","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b100","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b100","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b100","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b100","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b100","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-b100","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-b100","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b100","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-b100","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-b100","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b100","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-b200","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-b200","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-b200","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-b200","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-b200","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-b200","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-b200","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-b200","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-b200","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-b200","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b200","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-b200","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-b200","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-b200","baichuan-m3-235b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b200","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,null,null],["nvidia-b200","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-b200","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-b200","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-b200","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-b200","command-a-plus-05-2026-bf16","cuda","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["nvidia-b200","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-b200","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-b200","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b200","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-b200","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b200","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-b200","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-b200","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-b200","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-b200","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-b200","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-b200","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-b200","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-b200","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-b200","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-b200","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b200","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-b200","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-b200","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b200","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b200","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b200","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b200","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-b200","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-b200","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-5","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-6-reap-268b-a32b","cuda","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-7","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-7-reap-218b-a32b","cuda","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-4-7-reap-268b-a32b","cuda","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-b200","glm-5-1","cuda","na","IQ2_XXS",8192,197.58,null,null,null,null,"no_measured_total"],["nvidia-b200","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-b200","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-b200","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-b200","glm-5-3-flash-bf16","cuda","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["nvidia-b200","gpt-oss-120b","cuda","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["nvidia-b200","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-b200","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-b200","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-b200","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b200","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-b200","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-b200","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-b200","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-b200","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-b200","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-b200","holo2-235b-a22b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b200","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b200","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-b200","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-b200","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-b200","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b200","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-b200","hy3","cuda","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["nvidia-b200","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","intern-s2-397b","cuda","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["nvidia-b200","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-b200","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-b200","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-b200","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b200","k-exaone-236b-a23b","cuda","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["nvidia-b200","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-b200","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-b200","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-b200","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-b200","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-b200","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-b200","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-b200","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-b200","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-b200","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-b200","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-b200","laguna-s-2-1","cuda","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["nvidia-b200","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-b200","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b200","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-b200","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-b200","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-b200","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-b200","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b200","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-b200","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-b200","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-b200","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-v2-5","cuda","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-b200","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-v2-6-flash-mopd","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-v2-6-flash-rl","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-b200","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-b200","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-b200","mimo-v2-flash","cuda","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-b200","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-b200","minimax-m2","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b200","minimax-m2-1","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b200","minimax-m2-5","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-b200","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-b200","minimax-m2-7","cuda","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-b200","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-b200","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-b200","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-b200","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-b200","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-b200","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-b200","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-b200","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-b200","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-b200","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b200","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-b200","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-b200","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-b200","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-b200","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-b200","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-b200","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-b200","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-235b-a22b","cuda","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-235b-a22b-instruct-2507","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-397b-a17b","cuda","na","Q3_K_M",8192,175.62,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-b200","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-480b-a35b-instruct","cuda","na","Q2_K",8192,174.28,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-coder-reap-363b-a35b","cuda","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-nemotron-235b-a22b-genrm","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-235b-a22b-instruct","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-b200","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-b200","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-b200","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b200","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-b200","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-b200","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-b200","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b200","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-b200","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-b200","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-b200","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-b200","step-3-7-flash","cuda","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["nvidia-b200","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b200","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b200","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b200","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-b200","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-b200","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-b200","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-large-base","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-large-thinking","cuda","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-large-truebase","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-b200","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-b200","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-b200","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b200","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-b200","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-b200","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-b200","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b200","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-b200","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-b200","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-b200","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-b200","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-b200","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-b200","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-geforce-gtx-1050-ti","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","apriel-1-6-15b-thinker","cuda","no","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","armorocr","cuda","no","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","bielik-minitron-7b-v3-0-instruct","cuda","no","Q4_K_M",8192,6.94,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","eurollm-9b-instruct-2512","cuda","no","Q2_K",8192,6.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","frogmini-14b-2510","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-2-9b-it","cuda","no","IQ2_M",8192,7.67,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-3-12b-it","cuda","no","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-12b-it","cuda","no","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-3-3-8b-instruct","cuda","no","Q2_K",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-1-8b","cuda","no","Q3_K_M",8192,6.68,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-4-2-8b","cuda","no","Q2_K",8192,5.8,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-guardian-3-2-8b-factuality-detection","cuda","no","Q2_K",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","granite-guardian-4-1-8b","cuda","no","Q2_K",8192,5.8,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-8b-a1b","cuda","no","Q4_0",8192,6.12,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","lfm2-8b-a1b","cuda","no","Q4_0",8192,6.02,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mellum2-12b-a2-5b-base","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mellum2-12b-a2-5b-instruct","cuda","no","IQ2_M",8192,6.5,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mellum2-12b-a2-5b-instruct-sft","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mellum2-12b-a2-5b-thinking","cuda","no","IQ2_M",8192,6.5,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mellum2-12b-a2-5b-thinking-sft","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","minicpm-o-4-5","cuda","no","Q4_0",8192,6.84,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ministral-3-8b-instruct-2512","cuda","no","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ministral-3-8b-reasoning-2512","cuda","no","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","mistral-nemo-instruct-2407","cuda","no","IQ2_M",8192,6.65,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nemotron-cascade-14b-thinking","cuda","no","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","nemotron-terminal-14b","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nouscoder-14b","cuda","no","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","nvidia-nemotron-nano-9b-v2","cuda","no","IQ2_M",8192,6.55,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1-7b-rl-zero-code","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1-7b-rl-zero-math","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-instruct","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-instruct-dpo","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-instruct-sft","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-rl-zero-code","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-rl-zero-general","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-rl-zero-if","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-rl-zero-math","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-rl-zero-mix","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-think","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-think-dpo","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmo-3-7b-think-sft","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","phi-3-5-mini-instruct","cuda","no","IQ2_M",8192,5.69,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-5-9b","cuda","no","Q3_K_M",8192,6.13,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-8b","cuda","no","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-nemotron-14b-brrm","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","translategemma-12b-it","cuda","no","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1050-ti","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","webworld-14b","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1050-ti","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1050-ti","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1060","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","aescode-8b","cuda","tight","Q4_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1060","agentcpm-explore","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1060","ai21-jamba-reasoning-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,130.4,null,null],["nvidia-geforce-gtx-1060","ai21-jamba2-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,130.4,null,null],["nvidia-geforce-gtx-1060","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","apertus-v1-1-1-5b","cuda","fits","Q8_0",4096,2.7,4096,false,132.1,null,null],["nvidia-geforce-gtx-1060","apertus-v1-1-1-5b-instruct","cuda","fits","Q8_0",4096,2.7,4096,false,132.1,null,null],["nvidia-geforce-gtx-1060","apertus-v1-1-4b","cuda","fits","IQ2_XXS",4096,2.72,4096,false,130.2,null,null],["nvidia-geforce-gtx-1060","apriel-1-6-15b-thinker","cuda","tight","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-gtx-1060","aprielguard","cuda","tight","Q6_K",8192,7.87,null,null,null,null,null],["nvidia-geforce-gtx-1060","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1060","astabrief-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","autoglm-phone-9b","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1060","autoglm-phone-9b-multilingual","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1060","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1060","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1060","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,"6",null],["nvidia-geforce-gtx-1060","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q5_K_M",8192,7.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","bitcpm-cann-3b-unquantized","cuda","fits","Q2_K",8192,2.86,8704,false,119.5,null,null],["nvidia-geforce-gtx-1060","caprl-qwen3vl-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","caprl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1060","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-gtx-1060","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,"6",null],["nvidia-geforce-gtx-1060","contextpilot-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","contextpilot-e4b","cuda","tight","Q8_0",8192,6.65,null,null,null,null,null],["nvidia-geforce-gtx-1060","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","cosmos-reason2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","d1-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1060","deepseek-r1-0528-qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","deepseek-r1-distill-llama-8b","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1060","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","deepseek-r1-distill-qwen-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1060","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1060","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1060","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1060","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,"7",null],["nvidia-geforce-gtx-1060","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"7",null],["nvidia-geforce-gtx-1060","eurollm-9b-instruct-2512","cuda","tight","Q4_K_M",8192,7.84,null,null,null,null,null],["nvidia-geforce-gtx-1060","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q3_K_M",8192,2.75,13056,false,391.6,null,null],["nvidia-geforce-gtx-1060","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","fara-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","fara1-5-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1060","fara1-5-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","frogmini-14b-2510","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","frognano-4b-2609","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1060","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,337.2,null,null],["nvidia-geforce-gtx-1060","gelab-zero-4b-preview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-2-9b-it","cuda","tight","IQ3_XXS",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-3-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-3-1b-it","cuda","fits","Q8_0",8192,2.68,32768,false,173.3,null,null],["nvidia-geforce-gtx-1060","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-3-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-4-12b-it","cuda","tight","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"8",null],["nvidia-geforce-gtx-1060","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","gemma-4-e2b","cuda","fits","Q3_K_M",8192,2.86,9728,false,146,null,null],["nvidia-geforce-gtx-1060","gemma-4-e2b-it","cuda","fits","Q3_K_M",8192,2.8,16896,false,152.8,null,null],["nvidia-geforce-gtx-1060","gemma-4-e4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","gemma-4-e4b-it","cuda","tight","Q8_0",8192,6.86,null,null,null,null,null],["nvidia-geforce-gtx-1060","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","glm-4-6v-flash","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1060","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,"7",null],["nvidia-geforce-gtx-1060","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1060","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1060","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-gtx-1060","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","granite-3-3-8b-instruct","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-4-0-1b","cuda","fits","Q3_K_M",8192,2.78,9216,false,125.7,null,null],["nvidia-geforce-gtx-1060","granite-4-0-350m","cuda","fits","BF16",8192,2.2,30464,false,204.3,null,null],["nvidia-geforce-gtx-1060","granite-4-0-h-1b","cuda","fits","Q6_K",8192,2.75,20480,false,151.3,null,null],["nvidia-geforce-gtx-1060","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,268.6,null,null],["nvidia-geforce-gtx-1060","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","granite-4-1-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","granite-4-2-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-4-2-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-guardian-4-0-3b-toxicity-ja","cuda","tight","Q6_K",8192,4.67,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-guardian-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1060","granite-vision-4-1-4b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1060","harc-llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","harc-qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","hipo-1-7b","cuda","fits","IQ2_XXS",8192,2.82,8704,false,126,null,null],["nvidia-geforce-gtx-1060","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,48896,false,266.9,null,null],["nvidia-geforce-gtx-1060","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","holo-3-1-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1060","holo-3-1-9b","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1060","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1060","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","holo2-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","holo2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","hunyuanocr","cuda","fits","Q6_K",8192,2.5,11776,false,153.9,null,null],["nvidia-geforce-gtx-1060","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1060","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-4b-baseline","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-4b-multiview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1060","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1060","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,"6",null],["nvidia-geforce-gtx-1060","januscoder-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","januscoderv-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1060","kanana-2-3b-base","cuda","tight","Q6_K",8192,4.89,null,null,null,null,null],["nvidia-geforce-gtx-1060","kanana-2-3b-instruct","cuda","tight","Q8_0",8192,5.65,null,null,null,null,null],["nvidia-geforce-gtx-1060","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1060","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1060","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1060","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1060","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"8",null],["nvidia-geforce-gtx-1060","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1060","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1060","lfm2-2-6b-exp","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1060","lfm2-2-6b-longevity","cuda","fits","IQ4_XS",8192,2.8,12288,false,123.9,null,null],["nvidia-geforce-gtx-1060","lfm2-2-6b-transcript","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1060","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","lfm2-5-1-2b-base","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-1-2b-instruct","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-1-2b-jp","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-1-2b-jp-202606","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-1-2b-thinking","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-2-6b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","lfm2-5-2-6b-base","cuda","fits","Q3_K_M",8192,2.74,15360,false,128.6,null,null],["nvidia-geforce-gtx-1060","lfm2-5-230m","cuda","fits","BF16",8192,1.83,82432,false,342.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","lfm2-5-350m","cuda","fits","BF16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1060","lfm2-5-8b-a1b","cuda","tight","Q5_K_M",8192,7.28,null,null,null,null,null],["nvidia-geforce-gtx-1060","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,94208,false,490.2,null,null],["nvidia-geforce-gtx-1060","lfm2-5-vl-1-6b","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-vl-1-6b-extract","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1060","lfm2-5-vl-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1060","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1060","lfm2-8b-a1b","cuda","tight","Q5_K_M",8192,7.18,null,null,null,null,null],["nvidia-geforce-gtx-1060","lfm2-vl-3b","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1060","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1060","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1060","llama-3-2-1b-instruct","cuda","fits","Q8_0",8192,2.83,9472,false,121.4,null,null],["nvidia-geforce-gtx-1060","llama-3-2-3b-instruct","cuda","tight","Q8_0",8192,5.55,null,null,null,null,null],["nvidia-geforce-gtx-1060","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","mathform-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","medgemma-1-5-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1060","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,"6",null],["nvidia-geforce-gtx-1060","mellum2-12b-a2-5b-base","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","mellum2-12b-a2-5b-instruct","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1060","mellum2-12b-a2-5b-instruct-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","mellum2-12b-a2-5b-thinking","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1060","mellum2-12b-a2-5b-thinking-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","mimo-embodied-7b","cuda","tight","Q5_K_M",8192,7.42,null,null,null,null,null],["nvidia-geforce-gtx-1060","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-6-distill-qwen-9b","cuda","tight","Q5_K_M",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1060","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1060","minicpm-o-4-5","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","minicpm-v-4-6","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1060","minicpm-v-4-6-thinking","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1060","minicpm-v-4-7-1b","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1060","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1060","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1060","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1060","minicpm5-2b","cuda","fits","Q3_K_M",8192,2.68,12288,false,134,null,null],["nvidia-geforce-gtx-1060","minicpm5-2b-base","cuda","fits","Q3_K_M",8192,2.77,10240,false,126,null,null],["nvidia-geforce-gtx-1060","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1060","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1060","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1060","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-gtx-1060","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1060","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1060","ministral-3-3b-instruct-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1060","ministral-3-3b-reasoning-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1060","ministral-3-8b-instruct-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1060","ministral-3-8b-reasoning-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1060","mistral-7b-instruct-v0-2","cuda","tight","Q5_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1060","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1060","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","mistral-nemo-instruct-2407","cuda","tight","Q2_K",8192,7.07,null,null,null,null,null],["nvidia-geforce-gtx-1060","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1060","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1060","nemotron-3-content-safety","cuda","tight","Q6_K",8192,5.37,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nemotron-cascade-14b-thinking","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nemotron-cascade-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-cascade-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-orchestrator-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-terminal-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nemotron-terminal-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nouscoder-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-nano-4b-bf16","cuda","tight","Q8_0",8192,5.46,null,null,null,null,null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","nvidia-nemotron-nano-9b-v2","cuda","tight","Q4_K_M",8192,7.98,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-1-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-1-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.24,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","olmo-3-7b-instruct","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-instruct-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-instruct-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-rl-zero-general","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-rl-zero-if","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-rl-zero-mix","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-think","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-think-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmo-3-7b-think-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1060","olmocr-2-7b-1025","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","phi-3-5-mini-instruct","cuda","tight","Q6_K",8192,7.43,null,null,null,null,null],["nvidia-geforce-gtx-1060","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1060","phi-4-mini-instruct","cuda","tight","Q8_0",8192,6.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1060","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen2-5-3b-instruct","cuda","fits","Q2_K",8192,2.86,8448,false,122.2,null,null],["nvidia-geforce-gtx-1060","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen2-5-coder-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen2-5-vl-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen2-5-vl-7b-surg-cholect50","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-0-6b","cuda","fits","Q8_0",8192,2.86,8192,false,122.1,null,null],["nvidia-geforce-gtx-1060","qwen3-1-7b","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-4b-instruct-2507","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-5-0-8b","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1060","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,48896,false,266.9,null,null],["nvidia-geforce-gtx-1060","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-5-2b","cuda","fits","Q4_0",8192,2.87,8192,false,147.2,null,null],["nvidia-geforce-gtx-1060","qwen3-5-2b-base","cuda","fits","Q4_0",8192,2.86,8960,false,148.3,null,null],["nvidia-geforce-gtx-1060","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"7",null],["nvidia-geforce-gtx-1060","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-5-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-5-4b-base","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-5-9b","cuda","tight","Q5_K_M",8192,7.74,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-5-9b-base","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8",null],["nvidia-geforce-gtx-1060","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,"5",null],["nvidia-geforce-gtx-1060","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-nemotron-14b-brrm","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-nemotron-8b-brrm","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1060","qwen3-vl-2b-instruct","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-vl-2b-thinking","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","qwen3-vl-4b-instruct","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-vl-4b-thinking","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-vl-8b-instruct","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwen3-vl-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","riva-translate-4b-instruct-v1-1","cuda","tight","Q6_K",8192,5.97,null,null,null,null,null],["nvidia-geforce-gtx-1060","rlvr-8b-0926","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","rnj-1-instruct","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1060","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","singguard-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","smollm3-3b","cuda","tight","BF16",8192,7.9,null,null,null,null,null],["nvidia-geforce-gtx-1060","smollm3-3b-gsm8k-sft","cuda","fits","IQ2_XXS",8192,2.78,9472,false,125.7,null,null],["nvidia-geforce-gtx-1060","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","spatial-ssrl-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","spatial-ssrl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1060","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1060","step3-vl-10b-base","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","tiny-aya-earth","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1060","tiny-aya-fire","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1060","tiny-aya-global","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1060","tiny-aya-water","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1060","translategemma-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1060","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","translategemma-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1060","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1060","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1060","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1060","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1060","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,"6",null],["nvidia-geforce-gtx-1060","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,"6",null],["nvidia-geforce-gtx-1060","trinity-nano-base","cuda","tight","Q6_K",8192,6.67,null,null,null,null,null],["nvidia-geforce-gtx-1060","trinity-nano-base-pre-anneal","cuda","tight","Q6_K",4096,6.43,null,null,null,null,null],["nvidia-geforce-gtx-1060","trinity-nano-preview","cuda","tight","Q8_0",8192,8.08,null,null,null,null,null],["nvidia-geforce-gtx-1060","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","ui-mate-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","ui-venus-1-5-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","ui-venus-1-5-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","ui-venus-2-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1060","userrepgen-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1060","webworld-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1060","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1060","webworld-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1060","x-reasoner-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","youtu-llm-2b","cuda","fits","Q4_K_M",8192,2.78,10496,false,125.5,null,null],["nvidia-geforce-gtx-1060","youtu-llm-2b-base","cuda","fits","Q4_K_M",8192,2.78,10496,false,125.5,null,null],["nvidia-geforce-gtx-1060","youtu-vl-4b-instruct","cuda","tight","Q6_K",8192,5.91,null,null,null,null,null],["nvidia-geforce-gtx-1060","zwz-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1060","zwz-4b","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1060","zwz-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1060","zwz-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1070","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-gtx-1070","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-gtx-1070","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,79.1,null,null],["nvidia-geforce-gtx-1070","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,79.1,null,null],["nvidia-geforce-gtx-1070","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-gtx-1070","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,97.8,null,null],["nvidia-geforce-gtx-1070","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,97.8,null,null],["nvidia-geforce-gtx-1070","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,79.7,null,null],["nvidia-geforce-gtx-1070","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,73.7,null,null],["nvidia-geforce-gtx-1070","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1070","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,71.8,null,null],["nvidia-geforce-gtx-1070","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1070","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-gtx-1070","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,83.3,null,null],["nvidia-geforce-gtx-1070","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,89.2,null,null],["nvidia-geforce-gtx-1070","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1070","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-gtx-1070","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,81.8,null,null],["nvidia-geforce-gtx-1070","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,85.3,null,null],["nvidia-geforce-gtx-1070","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1070","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1070","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1070","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1070","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1070","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1070","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-gtx-1070","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-gtx-1070","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-gtx-1070","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,416.5,null,null],["nvidia-geforce-gtx-1070","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-gtx-1070","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-gtx-1070","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,81.5,null,null],["nvidia-geforce-gtx-1070","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,85.7,null,null],["nvidia-geforce-gtx-1070","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,449.6,null,null],["nvidia-geforce-gtx-1070","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-gtx-1070","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-gtx-1070","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1070","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,125.2,null,null],["nvidia-geforce-gtx-1070","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1070","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-gtx-1070","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-gtx-1070","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-gtx-1070","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-gtx-1070","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-gtx-1070","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-gtx-1070","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,130.7,null,null],["nvidia-geforce-gtx-1070","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,98.7,null,null],["nvidia-geforce-gtx-1070","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,80.9,null,null],["nvidia-geforce-gtx-1070","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,80.5,null,null],["nvidia-geforce-gtx-1070","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-gtx-1070","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1070","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1070","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-gtx-1070","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1070","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,106.4,null,null],["nvidia-geforce-gtx-1070","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,272.4,null,null],["nvidia-geforce-gtx-1070","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,85.6,null,null],["nvidia-geforce-gtx-1070","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,358.1,null,null],["nvidia-geforce-gtx-1070","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1070","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,77.7,null,null],["nvidia-geforce-gtx-1070","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,108.9,null,null],["nvidia-geforce-gtx-1070","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,355.8,null,null],["nvidia-geforce-gtx-1070","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1070","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,86.3,null,null],["nvidia-geforce-gtx-1070","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1070","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-gtx-1070","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-gtx-1070","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1070","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,135.9,null,null],["nvidia-geforce-gtx-1070","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1070","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1070","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1070","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-gtx-1070","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1070","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,76.3,null,null],["nvidia-geforce-gtx-1070","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,76.3,null,null],["nvidia-geforce-gtx-1070","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-gtx-1070","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1070","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1070","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1070","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1070","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-gtx-1070","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-gtx-1070","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1070","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1070","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-gtx-1070","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,85.3,null,null],["nvidia-geforce-gtx-1070","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,109,null,null],["nvidia-geforce-gtx-1070","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,457,null,null],["nvidia-geforce-gtx-1070","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-gtx-1070","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-gtx-1070","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,653.6,null,null],["nvidia-geforce-gtx-1070","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,85.3,null,null],["nvidia-geforce-gtx-1070","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-gtx-1070","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1070","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-gtx-1070","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-gtx-1070","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,93.4,null,null],["nvidia-geforce-gtx-1070","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,71.6,null,null],["nvidia-geforce-gtx-1070","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1070","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1070","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,76.6,null,null],["nvidia-geforce-gtx-1070","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1070","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-gtx-1070","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,93.3,null,null],["nvidia-geforce-gtx-1070","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,116.5,null,null],["nvidia-geforce-gtx-1070","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1070","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1070","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,76.7,null,null],["nvidia-geforce-gtx-1070","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,76.7,null,null],["nvidia-geforce-gtx-1070","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1070","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1070","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,72.8,null,null],["nvidia-geforce-gtx-1070","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1070","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-gtx-1070","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1070","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-gtx-1070","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1070","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-gtx-1070","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-gtx-1070","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-gtx-1070","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,86,null,null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1070","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-gtx-1070","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-gtx-1070","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-gtx-1070","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,80.4,null,null],["nvidia-geforce-gtx-1070","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,71.5,null,null],["nvidia-geforce-gtx-1070","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,120.1,null,null],["nvidia-geforce-gtx-1070","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-gtx-1070","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-gtx-1070","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-gtx-1070","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,355.8,null,null],["nvidia-geforce-gtx-1070","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-gtx-1070","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,121.8,null,null],["nvidia-geforce-gtx-1070","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,155.5,null,null],["nvidia-geforce-gtx-1070","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-gtx-1070","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-gtx-1070","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,85.4,null,null],["nvidia-geforce-gtx-1070","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,86.3,null,null],["nvidia-geforce-gtx-1070","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-gtx-1070","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-gtx-1070","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-gtx-1070","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1070","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1070","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1070","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-gtx-1070","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,71,null,null],["nvidia-geforce-gtx-1070","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-gtx-1070","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,81.9,null,null],["nvidia-geforce-gtx-1070","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,81.9,null,null],["nvidia-geforce-gtx-1070","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1070","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1070","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1070","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1070","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-gtx-1070","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-gtx-1070","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-gtx-1070","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,369.8,null,null],["nvidia-geforce-gtx-1070","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,382.8,null,null],["nvidia-geforce-gtx-1070","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,356.8,null,null],["nvidia-geforce-gtx-1070","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-gtx-1070","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-gtx-1070","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,85.7,null,null],["nvidia-geforce-gtx-1070","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,133.3,null,null],["nvidia-geforce-gtx-1070","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,133.3,null,null],["nvidia-geforce-gtx-1070","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,77,null,null],["nvidia-geforce-gtx-1070","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,79.1,null,null],["nvidia-geforce-gtx-1070-ti","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,79.1,null,null],["nvidia-geforce-gtx-1070-ti","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,97.8,null,null],["nvidia-geforce-gtx-1070-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,97.8,null,null],["nvidia-geforce-gtx-1070-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,79.7,null,null],["nvidia-geforce-gtx-1070-ti","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,73.7,null,null],["nvidia-geforce-gtx-1070-ti","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,71.8,null,null],["nvidia-geforce-gtx-1070-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,83.3,null,null],["nvidia-geforce-gtx-1070-ti","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,89.2,null,null],["nvidia-geforce-gtx-1070-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,81.8,null,null],["nvidia-geforce-gtx-1070-ti","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,85.3,null,null],["nvidia-geforce-gtx-1070-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,416.5,null,null],["nvidia-geforce-gtx-1070-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,81.5,null,null],["nvidia-geforce-gtx-1070-ti","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,85.7,null,null],["nvidia-geforce-gtx-1070-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,449.6,null,null],["nvidia-geforce-gtx-1070-ti","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,125.2,null,null],["nvidia-geforce-gtx-1070-ti","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,130.7,null,null],["nvidia-geforce-gtx-1070-ti","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,98.7,null,null],["nvidia-geforce-gtx-1070-ti","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,80.9,null,null],["nvidia-geforce-gtx-1070-ti","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,80.5,null,null],["nvidia-geforce-gtx-1070-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,106.4,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,272.4,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,85.6,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,358.1,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070-ti","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070-ti","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,73.9,null,null],["nvidia-geforce-gtx-1070-ti","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,77.7,null,null],["nvidia-geforce-gtx-1070-ti","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,108.9,null,null],["nvidia-geforce-gtx-1070-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,355.8,null,null],["nvidia-geforce-gtx-1070-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,86.3,null,null],["nvidia-geforce-gtx-1070-ti","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,135.9,null,null],["nvidia-geforce-gtx-1070-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,76.3,null,null],["nvidia-geforce-gtx-1070-ti","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,76.3,null,null],["nvidia-geforce-gtx-1070-ti","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,85.3,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,109,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,457,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,653.6,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,104.8,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,85.3,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,316.1,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,89.4,null,null],["nvidia-geforce-gtx-1070-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,93.4,null,null],["nvidia-geforce-gtx-1070-ti","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,277.2,null,null],["nvidia-geforce-gtx-1070-ti","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,93.3,null,null],["nvidia-geforce-gtx-1070-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,116.5,null,null],["nvidia-geforce-gtx-1070-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,76.7,null,null],["nvidia-geforce-gtx-1070-ti","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,76.7,null,null],["nvidia-geforce-gtx-1070-ti","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,72.8,null,null],["nvidia-geforce-gtx-1070-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-gtx-1070-ti","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,86,null,null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,80.4,null,null],["nvidia-geforce-gtx-1070-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,71.5,null,null],["nvidia-geforce-gtx-1070-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,77.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,120.1,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,159.4,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,355.8,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,121.8,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,155.5,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-gtx-1070-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,85.4,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,86.3,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-gtx-1070-ti","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-gtx-1070-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,71,null,null],["nvidia-geforce-gtx-1070-ti","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,81.9,null,null],["nvidia-geforce-gtx-1070-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,81.9,null,null],["nvidia-geforce-gtx-1070-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1070-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070-ti","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070-ti","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070-ti","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,102,null,null],["nvidia-geforce-gtx-1070-ti","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,92.3,null,null],["nvidia-geforce-gtx-1070-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1070-ti","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,369.8,null,null],["nvidia-geforce-gtx-1070-ti","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,382.8,null,null],["nvidia-geforce-gtx-1070-ti","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,356.8,null,null],["nvidia-geforce-gtx-1070-ti","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-gtx-1070-ti","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1070-ti","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,85.7,null,null],["nvidia-geforce-gtx-1070-ti","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1070-ti","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1070-ti","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,133.3,null,null],["nvidia-geforce-gtx-1070-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,133.3,null,null],["nvidia-geforce-gtx-1070-ti","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,77,null,null],["nvidia-geforce-gtx-1070-ti","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,92.5,null,null],["nvidia-geforce-gtx-1070-ti","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,71.6,null,null],["nvidia-geforce-gtx-1070-ti","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,76.6,null,null],["nvidia-geforce-gtx-1070-ti","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,73.4,null,null],["nvidia-geforce-gtx-1080","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-gtx-1080","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-gtx-1080","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,98.9,null,null],["nvidia-geforce-gtx-1080","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,98.9,null,null],["nvidia-geforce-gtx-1080","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-gtx-1080","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,122.3,null,null],["nvidia-geforce-gtx-1080","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,122.3,null,null],["nvidia-geforce-gtx-1080","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,99.7,null,null],["nvidia-geforce-gtx-1080","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,92.1,null,null],["nvidia-geforce-gtx-1080","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1080","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,89.8,null,null],["nvidia-geforce-gtx-1080","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1080","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-gtx-1080","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,104.1,null,null],["nvidia-geforce-gtx-1080","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,111.4,null,null],["nvidia-geforce-gtx-1080","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1080","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-gtx-1080","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,102.3,null,null],["nvidia-geforce-gtx-1080","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1080","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,106.6,null,null],["nvidia-geforce-gtx-1080","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1080","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1080","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1080","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1080","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,96.9,null,null],["nvidia-geforce-gtx-1080","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1080","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1080","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1080","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1080","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-gtx-1080","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-gtx-1080","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-gtx-1080","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,520.6,null,null],["nvidia-geforce-gtx-1080","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-gtx-1080","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-gtx-1080","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,101.8,null,null],["nvidia-geforce-gtx-1080","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1080","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1080","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,107.1,null,null],["nvidia-geforce-gtx-1080","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,562.1,null,null],["nvidia-geforce-gtx-1080","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-gtx-1080","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-gtx-1080","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1080","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,156.5,null,null],["nvidia-geforce-gtx-1080","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1080","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,115.4,null,null],["nvidia-geforce-gtx-1080","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-gtx-1080","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-gtx-1080","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-gtx-1080","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-gtx-1080","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-gtx-1080","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-gtx-1080","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,163.3,null,null],["nvidia-geforce-gtx-1080","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,123.4,null,null],["nvidia-geforce-gtx-1080","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,101.2,null,null],["nvidia-geforce-gtx-1080","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,100.7,null,null],["nvidia-geforce-gtx-1080","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-gtx-1080","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1080","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1080","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-gtx-1080","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1080","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,133,null,null],["nvidia-geforce-gtx-1080","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,340.5,null,null],["nvidia-geforce-gtx-1080","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,107,null,null],["nvidia-geforce-gtx-1080","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,447.6,null,null],["nvidia-geforce-gtx-1080","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1080","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,92.4,null,null],["nvidia-geforce-gtx-1080","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1080","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-gtx-1080","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,92.4,null,null],["nvidia-geforce-gtx-1080","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1080","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-gtx-1080","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,92.4,null,null],["nvidia-geforce-gtx-1080","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-gtx-1080","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,92.4,null,null],["nvidia-geforce-gtx-1080","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,97.2,null,null],["nvidia-geforce-gtx-1080","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-gtx-1080","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,136.1,null,null],["nvidia-geforce-gtx-1080","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,444.8,null,null],["nvidia-geforce-gtx-1080","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1080","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,107.9,null,null],["nvidia-geforce-gtx-1080","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1080","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-gtx-1080","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-gtx-1080","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-gtx-1080","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1080","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,169.9,null,null],["nvidia-geforce-gtx-1080","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1080","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1080","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1080","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-gtx-1080","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1080","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,95.4,null,null],["nvidia-geforce-gtx-1080","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,95.4,null,null],["nvidia-geforce-gtx-1080","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-gtx-1080","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1080","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1080","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1080","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1080","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-gtx-1080","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-gtx-1080","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-gtx-1080","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1080","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-gtx-1080","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,111.7,null,null],["nvidia-geforce-gtx-1080","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,111.7,null,null],["nvidia-geforce-gtx-1080","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,111.7,null,null],["nvidia-geforce-gtx-1080","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-gtx-1080","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,106.6,null,null],["nvidia-geforce-gtx-1080","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,136.3,null,null],["nvidia-geforce-gtx-1080","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,571.3,null,null],["nvidia-geforce-gtx-1080","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-gtx-1080","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,395.2,null,null],["nvidia-geforce-gtx-1080","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-gtx-1080","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,817,null,null],["nvidia-geforce-gtx-1080","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,131.1,null,null],["nvidia-geforce-gtx-1080","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,106.6,null,null],["nvidia-geforce-gtx-1080","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,395.2,null,null],["nvidia-geforce-gtx-1080","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,395.2,null,null],["nvidia-geforce-gtx-1080","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-gtx-1080","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,111.7,null,null],["nvidia-geforce-gtx-1080","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1080","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-gtx-1080","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-gtx-1080","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,116.8,null,null],["nvidia-geforce-gtx-1080","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,89.5,null,null],["nvidia-geforce-gtx-1080","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,115.4,null,null],["nvidia-geforce-gtx-1080","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1080","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1080","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1080","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1080","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-gtx-1080","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1080","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,95.8,null,null],["nvidia-geforce-gtx-1080","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1080","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1080","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,199.3,null,null],["nvidia-geforce-gtx-1080","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,199.3,null,null],["nvidia-geforce-gtx-1080","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,199.3,null,null],["nvidia-geforce-gtx-1080","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-gtx-1080","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,346.5,null,null],["nvidia-geforce-gtx-1080","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,346.5,null,null],["nvidia-geforce-gtx-1080","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,346.5,null,null],["nvidia-geforce-gtx-1080","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,116.7,null,null],["nvidia-geforce-gtx-1080","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,145.6,null,null],["nvidia-geforce-gtx-1080","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1080","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1080","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1080","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1080","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-gtx-1080","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,95.9,null,null],["nvidia-geforce-gtx-1080","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,95.9,null,null],["nvidia-geforce-gtx-1080","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1080","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-gtx-1080","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,91,null,null],["nvidia-geforce-gtx-1080","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1080","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-gtx-1080","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-gtx-1080","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-gtx-1080","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1080","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,115.4,null,null],["nvidia-geforce-gtx-1080","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-gtx-1080","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-gtx-1080","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1080","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-gtx-1080","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,107.5,null,null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-gtx-1080","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1080","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1080","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1080","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1080","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-gtx-1080","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1080","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-gtx-1080","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-gtx-1080","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-gtx-1080","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-gtx-1080","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-gtx-1080","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,100.5,null,null],["nvidia-geforce-gtx-1080","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1080","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,89.3,null,null],["nvidia-geforce-gtx-1080","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,96.9,null,null],["nvidia-geforce-gtx-1080","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-gtx-1080","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,96.9,null,null],["nvidia-geforce-gtx-1080","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,96.9,null,null],["nvidia-geforce-gtx-1080","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,96.9,null,null],["nvidia-geforce-gtx-1080","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,150.1,null,null],["nvidia-geforce-gtx-1080","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-gtx-1080","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-gtx-1080","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1080","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-gtx-1080","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,199.2,null,null],["nvidia-geforce-gtx-1080","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,444.8,null,null],["nvidia-geforce-gtx-1080","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-gtx-1080","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,152.3,null,null],["nvidia-geforce-gtx-1080","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,194.4,null,null],["nvidia-geforce-gtx-1080","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-gtx-1080","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-gtx-1080","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,106.7,null,null],["nvidia-geforce-gtx-1080","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,107.9,null,null],["nvidia-geforce-gtx-1080","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-gtx-1080","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-gtx-1080","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1080","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-gtx-1080","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1080","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1080","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1080","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-gtx-1080","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-gtx-1080","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,88.8,null,null],["nvidia-geforce-gtx-1080","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-gtx-1080","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1080","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,102.3,null,null],["nvidia-geforce-gtx-1080","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,102.3,null,null],["nvidia-geforce-gtx-1080","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1080","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,127.5,null,null],["nvidia-geforce-gtx-1080","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,127.5,null,null],["nvidia-geforce-gtx-1080","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,127.5,null,null],["nvidia-geforce-gtx-1080","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,127.5,null,null],["nvidia-geforce-gtx-1080","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-gtx-1080","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-gtx-1080","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,115.4,null,null],["nvidia-geforce-gtx-1080","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1080","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-gtx-1080","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-gtx-1080","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-gtx-1080","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,462.2,null,null],["nvidia-geforce-gtx-1080","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,478.4,null,null],["nvidia-geforce-gtx-1080","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,445.9,null,null],["nvidia-geforce-gtx-1080","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-gtx-1080","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1080","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-gtx-1080","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-gtx-1080","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-gtx-1080","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,107.1,null,null],["nvidia-geforce-gtx-1080","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-gtx-1080","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-gtx-1080","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-gtx-1080","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,166.7,null,null],["nvidia-geforce-gtx-1080","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,166.7,null,null],["nvidia-geforce-gtx-1080","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,96.2,null,null],["nvidia-geforce-gtx-1080","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,115.6,null,null],["nvidia-geforce-gtx-1080","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,89.4,null,null],["nvidia-geforce-gtx-1080","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,95.7,null,null],["nvidia-geforce-gtx-1080","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,91.7,null,null],["nvidia-geforce-gtx-1080-ti","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","aescode-8b","cuda","fits","Q4_K_M",8192,7.27,12288,false,79.8,null,null],["nvidia-geforce-gtx-1080-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,22528,false,107.4,null,null],["nvidia-geforce-gtx-1080-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,207872,false,79.7,null,null],["nvidia-geforce-gtx-1080-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,207872,false,79.7,null,null],["nvidia-geforce-gtx-1080-ti","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,184.9,null,null],["nvidia-geforce-gtx-1080-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,184.9,null,null],["nvidia-geforce-gtx-1080-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,150.7,null,null],["nvidia-geforce-gtx-1080-ti","apriel-1-6-15b-thinker","cuda","fits","IQ2_M",8192,7.64,9216,false,74.6,null,null],["nvidia-geforce-gtx-1080-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,8192,false,72,null,null],["nvidia-geforce-gtx-1080-ti","armorocr","cuda","fits","Q4_K_M",8192,7.09,13568,false,82.3,null,null],["nvidia-geforce-gtx-1080-ti","astabrief-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","autoglm-phone-9b","cuda","fits","Q4_K_M",8192,7.34,20736,false,78.8,null,null],["nvidia-geforce-gtx-1080-ti","autoglm-phone-9b-multilingual","cuda","fits","Q4_K_M",8192,7.34,20736,false,78.8,null,null],["nvidia-geforce-gtx-1080-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","bielik-11b-v3-0-instruct","cuda","tight","Q6_K",8192,11.8,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q5_K_M",8192,7.7,9216,false,74,null,null],["nvidia-geforce-gtx-1080-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,157.5,null,null],["nvidia-geforce-gtx-1080-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","contextpilot-14b","cuda","tight","Q5_K_M",8192,12.65,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","contextpilot-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,76032,false,94.6,null,null],["nvidia-geforce-gtx-1080-ti","cosmos-reason2-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","cosmos-reason2-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,87.5,null,null],["nvidia-geforce-gtx-1080-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-distill-llama-8b","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-distill-qwen-14b","cuda","tight","Q5_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","devstral-small-2-24b-instruct-2512","cuda","tight","Q3_K_M",8192,13.55,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","eurollm-22b-2512","cuda","tight","Q3_K_M",8192,13.62,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","eurollm-22b-instruct-2512","cuda","tight","Q3_K_M",8192,13.62,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","eurollm-9b-instruct-2512","cuda","fits","Q4_K_M",8192,7.84,8192,false,72.3,null,null],["nvidia-geforce-gtx-1080-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,787.4,null,null],["nvidia-geforce-gtx-1080-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","fara-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","fara1-5-27b","cuda","tight","Q2_K",8192,13.61,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,51968,false,101.9,null,null],["nvidia-geforce-gtx-1080-ti","fara1-5-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,86.5,null,null],["nvidia-geforce-gtx-1080-ti","frogboss-32b-2510","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","frogmini-14b-2510","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,51968,false,101.9,null,null],["nvidia-geforce-gtx-1080-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,850.1,null,null],["nvidia-geforce-gtx-1080-ti","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","gemma-2-27b-it","cuda","tight","IQ2_M",8192,13.78,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-2-9b-it","cuda","fits","IQ2_M",8192,7.67,8192,false,87.3,null,null],["nvidia-geforce-gtx-1080-ti","gemma-3-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,236.7,null,null],["nvidia-geforce-gtx-1080-ti","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,109.7,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","gemma-4-12b-it","cuda","tight","Q6_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-26b-a4b-it","cuda","tight","Q2_K",8192,13.36,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,247,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,104,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,72960,false,93.5,null,null],["nvidia-geforce-gtx-1080-ti","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,64000,false,90.7,null,null],["nvidia-geforce-gtx-1080-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8",null],["nvidia-geforce-gtx-1080-ti","glm-4-6v-flash","cuda","fits","Q4_K_M",8192,7.34,20736,false,78.8,null,null],["nvidia-geforce-gtx-1080-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q3_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","granite-3-3-8b-instruct","cuda","fits","Q4_K_M",8192,7.44,10752,false,77,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,41216,false,123,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,515,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,161.8,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,677,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"2",null],["nvidia-geforce-gtx-1080-ti","granite-4-1-3b","cuda","fits","Q8_0",8192,5.48,37120,false,112.9,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-1-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,75,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"2",null],["nvidia-geforce-gtx-1080-ti","granite-4-2-3b","cuda","fits","Q8_0",8192,5.48,37120,false,112.9,null,null],["nvidia-geforce-gtx-1080-ti","granite-4-2-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,75,null,null],["nvidia-geforce-gtx-1080-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q4_K_M",8192,7.44,10752,false,77,null,null],["nvidia-geforce-gtx-1080-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,46848,false,139.8,null,null],["nvidia-geforce-gtx-1080-ti","granite-guardian-4-1-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,75,null,null],["nvidia-geforce-gtx-1080-ti","granite-vision-4-1-4b","cuda","fits","Q8_0",8192,5.48,37120,false,112.9,null,null],["nvidia-geforce-gtx-1080-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,205.8,null,null],["nvidia-geforce-gtx-1080-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,672.7,null,null],["nvidia-geforce-gtx-1080-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,52224,false,102.1,null,null],["nvidia-geforce-gtx-1080-ti","holo-3-1-9b","cuda","fits","Q5_K_M",8192,7.63,15360,false,80.3,null,null],["nvidia-geforce-gtx-1080-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","holo2-4b","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","holo2-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","holo4-27b","cuda","tight","IQ3_XXS",8192,13.08,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","holo4-35b-a3b","cuda","tight","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,257,null,null],["nvidia-geforce-gtx-1080-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","ising-calibration-1-35b-a3b","cuda","tight","IQ2_M",8192,13.14,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","januscoder-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","januscoder-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,30976,false,131.4,null,null],["nvidia-geforce-gtx-1080-ti","kanana-2-3b-instruct","cuda","fits","Q8_0",8192,5.65,25088,false,108.7,null,null],["nvidia-geforce-gtx-1080-ti","kat-coder-v2-5-dev","cuda","tight","IQ2_M",8192,13.54,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ2_M",8192,12.81,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,86784,false,91.8,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,86784,false,91.8,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,86784,false,91.8,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,72960,false,87.5,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,206.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,864,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,597.7,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-8b-a1b","cuda","fits","Q5_K_M",8192,7.28,50176,false,365.7,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1235.8,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,198.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,87.5,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,597.7,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,597.7,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-8b-a1b","cuda","fits","Q5_K_M",8192,7.18,57600,false,397.2,null,null],["nvidia-geforce-gtx-1080-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,86784,false,91.8,null,null],["nvidia-geforce-gtx-1080-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","llama-3-1-8b-instruct","cuda","fits","Q5_K_M",8192,7.59,10240,false,75.2,null,null],["nvidia-geforce-gtx-1080-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,122624,false,176.6,null,null],["nvidia-geforce-gtx-1080-ti","llama-3-2-3b-instruct","cuda","fits","Q8_0",8192,5.55,28416,false,111.2,null,null],["nvidia-geforce-gtx-1080-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8",null],["nvidia-geforce-gtx-1080-ti","mathform-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,109.7,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q6_K",8192,12.08,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-12b-a2-5b-base","cuda","fits","Q3_K_M",8192,7.7,18688,false,351.8,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q3_K_M",8192,7.56,27904,false,337.3,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q3_K_M",8192,7.7,18688,false,351.8,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q3_K_M",8192,7.56,27904,false,337.3,null,null],["nvidia-geforce-gtx-1080-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q3_K_M",8192,7.7,18688,false,351.8,null,null],["nvidia-geforce-gtx-1080-ti","mimo-embodied-7b","cuda","fits","Q5_K_M",8192,7.42,11264,false,77.8,null,null],["nvidia-geforce-gtx-1080-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","Q4_K_M",8192,7.14,29696,false,87.6,null,null],["nvidia-geforce-gtx-1080-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","minicpm-o-4-5","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,301.4,null,null],["nvidia-geforce-gtx-1080-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,301.4,null,null],["nvidia-geforce-gtx-1080-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,301.4,null,null],["nvidia-geforce-gtx-1080-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,524.1,null,null],["nvidia-geforce-gtx-1080-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,524.1,null,null],["nvidia-geforce-gtx-1080-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,524.1,null,null],["nvidia-geforce-gtx-1080-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,49664,false,99.8,null,null],["nvidia-geforce-gtx-1080-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,108544,false,220.2,null,null],["nvidia-geforce-gtx-1080-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"7",null],["nvidia-geforce-gtx-1080-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ministral-3-3b-instruct-2512","cuda","fits","Q8_0",8192,5.71,28416,false,107.2,null,null],["nvidia-geforce-gtx-1080-ti","ministral-3-3b-reasoning-2512","cuda","fits","Q8_0",8192,5.71,28416,false,107.2,null,null],["nvidia-geforce-gtx-1080-ti","ministral-3-8b-instruct-2512","cuda","fits","Q4_K_M",8192,7.19,13056,false,80.3,null,null],["nvidia-geforce-gtx-1080-ti","ministral-3-8b-reasoning-2512","cuda","fits","Q4_K_M",8192,7.19,13056,false,80.3,null,null],["nvidia-geforce-gtx-1080-ti","mistral-7b-instruct-v0-2","cuda","fits","Q5_K_M",8192,7.27,12544,false,79.2,null,null],["nvidia-geforce-gtx-1080-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","mistral-nemo-instruct-2407","cuda","fits","Q2_K",8192,7.07,13056,false,82,null,null],["nvidia-geforce-gtx-1080-ti","mistral-small-3-2-24b-instruct-2506","cuda","tight","Q3_K_M",8192,13.55,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8",null],["nvidia-geforce-gtx-1080-ti","muse-glimmer-30b","cuda","tight","IQ3_XXS",8192,12.61,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,121344,false,139.3,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","nemotron-cascade-14b-thinking","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","nemotron-cascade-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-cascade-8b-thinking","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-orchestrator-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-terminal-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-terminal-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","nemotron-terminal-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","north-mini-code-1-0","cuda","tight","Q2_K",8192,13.23,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","nouscoder-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q8_0",8192,5.46,141824,false,123.4,null,null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","Q4_0",8192,6.88,62976,false,94.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-1-7b-rl-zero-math","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-1125-32b","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","olmo-3-32b-think-dpo","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-32b-think-sft","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-instruct","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-instruct-dpo","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-instruct-sft","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-rl-zero-code","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-rl-zero-general","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-rl-zero-if","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-rl-zero-math","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-rl-zero-mix","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-think","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-think-dpo","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmo-3-7b-think-sft","cuda","fits","IQ2_XXS",8192,7.47,8960,false,103.2,null,null],["nvidia-geforce-gtx-1080-ti","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","phi-3-5-mini-instruct","cuda","fits","Q6_K",8192,7.43,9216,false,77.1,null,null],["nvidia-geforce-gtx-1080-ti","phi-4","cuda","tight","Q5_K_M",8192,12.78,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,18944,false,94,null,null],["nvidia-geforce-gtx-1080-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-gtx-1080-ti","qwen2-5-14b-instruct","cuda","tight","Q5_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,135.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,227,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,301.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,672.7,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-gtx-1080-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,185344,false,125.2,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,294,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen3-5-35b-a3b-base","cuda","tight","IQ2_M",8192,13.02,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,52224,false,102.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,52224,false,102.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-9b","cuda","fits","Q5_K_M",8192,7.74,12032,false,78.9,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-5-9b-base","cuda","fits","Q5_K_M",8192,7.63,15360,false,80.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen3-6-35b-a3b","cuda","tight","IQ2_M",8192,13.54,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","qwen3-8-27b","cuda","tight","IQ3_XXS",8192,13.79,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-8-3-6-27b-blend","cuda","tight","IQ3_XXS",8192,13.79,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-reap-25b-a3b","cuda","tight","Q3_K_M",8192,13.26,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","qwen3-nemotron-14b-brrm","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-8b-instruct","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","qwen3-vl-8b-thinking","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"4",null],["nvidia-geforce-gtx-1080-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,101.1,null,null],["nvidia-geforce-gtx-1080-ti","rlvr-8b-0926","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","rnj-1-instruct","cuda","fits","Q4_K_M",8192,7.34,12288,false,78.3,null,null],["nvidia-geforce-gtx-1080-ti","sera-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","singguard-2b","cuda","fits","F16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","smollm3-3b","cuda","fits","Q8_0",8192,5.08,45824,false,125,null,null],["nvidia-geforce-gtx-1080-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,55552,false,154.8,null,null],["nvidia-geforce-gtx-1080-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-gtx-1080-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,16128,false,88.3,null,null],["nvidia-geforce-gtx-1080-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"6",null],["nvidia-geforce-gtx-1080-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"7",null],["nvidia-geforce-gtx-1080-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","step3-vl-10b-base","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","tiny-aya-earth","cuda","fits","Q8_0",8192,5.64,94976,false,123,null,null],["nvidia-geforce-gtx-1080-ti","tiny-aya-fire","cuda","fits","Q8_0",8192,5.64,94976,false,123,null,null],["nvidia-geforce-gtx-1080-ti","tiny-aya-global","cuda","fits","Q8_0",8192,5.64,94976,false,123,null,null],["nvidia-geforce-gtx-1080-ti","tiny-aya-water","cuda","fits","Q8_0",8192,5.64,94976,false,123,null,null],["nvidia-geforce-gtx-1080-ti","translategemma-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,109.7,null,null],["nvidia-geforce-gtx-1080-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1080-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1080-ti","trinity-mini","cuda","tight","Q3_K_M",8192,13.65,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","trinity-mini-base","cuda","tight","IQ3_XXS",8192,11.76,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","trinity-mini-base-pre-anneal","cuda","tight","Q3_K_M",4096,13.8,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,81408,false,537.4,null,null],["nvidia-geforce-gtx-1080-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,574.9,null,null],["nvidia-geforce-gtx-1080-ti","trinity-nano-preview","cuda","fits","Q6_K",8192,6.69,80640,false,529.3,null,null],["nvidia-geforce-gtx-1080-ti","ui-mate-27b","cuda","tight","Q2_K",8192,13.61,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ui-mate-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,86.5,null,null],["nvidia-geforce-gtx-1080-ti","ui-mate-democua-27b","cuda","tight","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","ui-venus-1-5-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","ui-venus-2-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,86.5,null,null],["nvidia-geforce-gtx-1080-ti","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,51968,false,101.9,null,null],["nvidia-geforce-gtx-1080-ti","webworld-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,76.5,null,null],["nvidia-geforce-gtx-1080-ti","webworld-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1080-ti","webworld-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1080-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,252.1,null,null],["nvidia-geforce-gtx-1080-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,252.1,null,null],["nvidia-geforce-gtx-1080-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,109.6,null,null],["nvidia-geforce-gtx-1080-ti","zwz-2b","cuda","fits","F16",8192,5.62,27904,false,110.5,null,null],["nvidia-geforce-gtx-1080-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,22528,false,107.4,null,null],["nvidia-geforce-gtx-1080-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,15104,false,77.2,null,null],["nvidia-geforce-gtx-1080-ti","zwz-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,73.1,null,null],["nvidia-geforce-gtx-1650","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-gtx-1650","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-gtx-1650","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","apriel-1-6-15b-thinker","cuda","no","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-gtx-1650","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","armorocr","cuda","no","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1650","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1650","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-gtx-1650","bielik-minitron-7b-v3-0-instruct","cuda","no","Q4_K_M",8192,6.94,null,null,null,null,null],["nvidia-geforce-gtx-1650","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1650","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-gtx-1650","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,null,null],["nvidia-geforce-gtx-1650","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1650","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-geforce-gtx-1650","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,null,null],["nvidia-geforce-gtx-1650","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1650","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1650","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1650","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1650","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"over",null],["nvidia-geforce-gtx-1650","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-gtx-1650","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,null,null],["nvidia-geforce-gtx-1650","eurollm-9b-instruct-2512","cuda","no","Q2_K",8192,6.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,null,null],["nvidia-geforce-gtx-1650","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,null,null],["nvidia-geforce-gtx-1650","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","frogmini-14b-2510","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1650","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-2-9b-it","cuda","no","IQ2_M",8192,7.67,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-3-12b-it","cuda","no","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-12b-it","cuda","no","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,null,null],["nvidia-geforce-gtx-1650","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-geforce-gtx-1650","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-gtx-1650","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-gtx-1650","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1650","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1650","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-gtx-1650","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-3-3-8b-instruct","cuda","no","Q2_K",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-1-8b","cuda","no","Q3_K_M",8192,6.68,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-4-2-8b","cuda","no","Q2_K",8192,5.8,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-guardian-3-2-8b-factuality-detection","cuda","no","Q2_K",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","granite-guardian-4-1-8b","cuda","no","Q2_K",8192,5.8,null,null,null,null,null],["nvidia-geforce-gtx-1650","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-gtx-1650","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-gtx-1650","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1650","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1650","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-gtx-1650","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-gtx-1650","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-geforce-gtx-1650","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1650","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1650","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"over",null],["nvidia-geforce-gtx-1650","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1650","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-gtx-1650","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-gtx-1650","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,null,null],["nvidia-geforce-gtx-1650","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1650","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-gtx-1650","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-geforce-gtx-1650","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1650","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1650","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1650","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1650","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-gtx-1650","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-gtx-1650","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,null,null],["nvidia-geforce-gtx-1650","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1650","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-gtx-1650","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-gtx-1650","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-gtx-1650","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-8b-a1b","cuda","no","Q4_0",8192,6.12,null,null,null,null,null],["nvidia-geforce-gtx-1650","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","lfm2-8b-a1b","cuda","no","Q4_0",8192,6.02,null,null,null,null,null],["nvidia-geforce-gtx-1650","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1650","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,null,null],["nvidia-geforce-gtx-1650","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-geforce-gtx-1650","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-gtx-1650","mellum2-12b-a2-5b-base","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1650","mellum2-12b-a2-5b-instruct","cuda","no","IQ2_M",8192,6.5,null,null,null,null,null],["nvidia-geforce-gtx-1650","mellum2-12b-a2-5b-instruct-sft","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1650","mellum2-12b-a2-5b-thinking","cuda","no","IQ2_M",8192,6.5,null,null,null,null,null],["nvidia-geforce-gtx-1650","mellum2-12b-a2-5b-thinking-sft","cuda","no","IQ2_XXS",8192,5.84,null,null,null,null,null],["nvidia-geforce-gtx-1650","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1650","minicpm-o-4-5","cuda","no","Q4_0",8192,6.84,null,null,null,null,null],["nvidia-geforce-gtx-1650","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,null,null],["nvidia-geforce-gtx-1650","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1650","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1650","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1650","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"over",null],["nvidia-geforce-gtx-1650","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-gtx-1650","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-geforce-gtx-1650","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-geforce-gtx-1650","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ministral-3-8b-instruct-2512","cuda","no","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1650","ministral-3-8b-reasoning-2512","cuda","no","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1650","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"over",null],["nvidia-geforce-gtx-1650","mistral-nemo-instruct-2407","cuda","no","IQ2_M",8192,6.65,null,null,null,null,null],["nvidia-geforce-gtx-1650","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-geforce-gtx-1650","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-gtx-1650","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1650","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-geforce-gtx-1650","nemotron-cascade-14b-thinking","cuda","no","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1650","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-geforce-gtx-1650","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","nemotron-terminal-14b","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1650","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,null,null],["nvidia-geforce-gtx-1650","nouscoder-14b","cuda","no","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"over",null],["nvidia-geforce-gtx-1650","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"over",null],["nvidia-geforce-gtx-1650","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-geforce-gtx-1650","nvidia-nemotron-nano-9b-v2","cuda","no","IQ2_M",8192,6.55,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1-7b-rl-zero-code","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1-7b-rl-zero-math","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-instruct","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-instruct-dpo","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-instruct-sft","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-rl-zero-code","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-rl-zero-general","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-rl-zero-if","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-rl-zero-math","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-rl-zero-mix","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-think","cuda","no","Q2_K",8192,8.17,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-think-dpo","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmo-3-7b-think-sft","cuda","no","IQ2_XXS",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1650","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,null,null],["nvidia-geforce-gtx-1650","phi-3-5-mini-instruct","cuda","no","IQ2_M",8192,5.69,null,null,null,null,null],["nvidia-geforce-gtx-1650","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,null,null],["nvidia-geforce-gtx-1650","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-5-9b","cuda","no","Q3_K_M",8192,6.13,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-8b","cuda","no","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-nemotron-14b-brrm","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1650","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-geforce-gtx-1650","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,null,null],["nvidia-geforce-gtx-1650","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-geforce-gtx-1650","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"over",null],["nvidia-geforce-gtx-1650","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-geforce-gtx-1650","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"over",null],["nvidia-geforce-gtx-1650","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1650","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","translategemma-12b-it","cuda","no","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1650","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-gtx-1650","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1650","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1650","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1650","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,null,null],["nvidia-geforce-gtx-1650","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,null,null],["nvidia-geforce-gtx-1650","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,null,null],["nvidia-geforce-gtx-1650","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,null,null],["nvidia-geforce-gtx-1650","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-gtx-1650","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-gtx-1650","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","webworld-14b","cuda","no","IQ2_XXS",8192,6.6,null,null,null,null,null],["nvidia-geforce-gtx-1650","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-gtx-1650","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1650","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"capacity_too_small"],["nvidia-geforce-gtx-1660","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","aescode-8b","cuda","tight","Q4_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1660","agentcpm-explore","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1660","ai21-jamba-reasoning-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,130.4,null,null],["nvidia-geforce-gtx-1660","ai21-jamba2-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,130.4,null,null],["nvidia-geforce-gtx-1660","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","apertus-v1-1-1-5b","cuda","fits","Q8_0",4096,2.7,4096,false,132.1,null,null],["nvidia-geforce-gtx-1660","apertus-v1-1-1-5b-instruct","cuda","fits","Q8_0",4096,2.7,4096,false,132.1,null,null],["nvidia-geforce-gtx-1660","apertus-v1-1-4b","cuda","fits","IQ2_XXS",4096,2.72,4096,false,130.2,null,null],["nvidia-geforce-gtx-1660","apriel-1-6-15b-thinker","cuda","tight","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-gtx-1660","aprielguard","cuda","tight","Q6_K",8192,7.87,null,null,null,null,null],["nvidia-geforce-gtx-1660","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1660","astabrief-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","autoglm-phone-9b","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660","autoglm-phone-9b-multilingual","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1660","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,"6",null],["nvidia-geforce-gtx-1660","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q5_K_M",8192,7.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","bitcpm-cann-3b-unquantized","cuda","fits","Q2_K",8192,2.86,8704,false,119.5,null,null],["nvidia-geforce-gtx-1660","caprl-qwen3vl-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","caprl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1660","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-gtx-1660","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,"6",null],["nvidia-geforce-gtx-1660","contextpilot-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","contextpilot-e4b","cuda","tight","Q8_0",8192,6.65,null,null,null,null,null],["nvidia-geforce-gtx-1660","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","cosmos-reason2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","d1-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1660","deepseek-r1-0528-qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","deepseek-r1-distill-llama-8b","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1660","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","deepseek-r1-distill-qwen-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1660","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1660","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1660","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1660","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,"7",null],["nvidia-geforce-gtx-1660","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"7",null],["nvidia-geforce-gtx-1660","eurollm-9b-instruct-2512","cuda","tight","Q4_K_M",8192,7.84,null,null,null,null,null],["nvidia-geforce-gtx-1660","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q3_K_M",8192,2.75,13056,false,391.6,null,null],["nvidia-geforce-gtx-1660","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","fara-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","fara1-5-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660","fara1-5-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","frogmini-14b-2510","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","frognano-4b-2609","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,337.2,null,null],["nvidia-geforce-gtx-1660","gelab-zero-4b-preview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-2-9b-it","cuda","tight","IQ3_XXS",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-3-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-3-1b-it","cuda","fits","Q8_0",8192,2.68,32768,false,173.3,null,null],["nvidia-geforce-gtx-1660","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-3-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-4-12b-it","cuda","tight","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"8",null],["nvidia-geforce-gtx-1660","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","gemma-4-e2b","cuda","fits","Q3_K_M",8192,2.86,9728,false,146,null,null],["nvidia-geforce-gtx-1660","gemma-4-e2b-it","cuda","fits","Q3_K_M",8192,2.8,16896,false,152.8,null,null],["nvidia-geforce-gtx-1660","gemma-4-e4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","gemma-4-e4b-it","cuda","tight","Q8_0",8192,6.86,null,null,null,null,null],["nvidia-geforce-gtx-1660","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","glm-4-6v-flash","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,"7",null],["nvidia-geforce-gtx-1660","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1660","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1660","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-gtx-1660","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","granite-3-3-8b-instruct","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-4-0-1b","cuda","fits","Q3_K_M",8192,2.78,9216,false,125.7,null,null],["nvidia-geforce-gtx-1660","granite-4-0-350m","cuda","fits","BF16",8192,2.2,30464,false,204.3,null,null],["nvidia-geforce-gtx-1660","granite-4-0-h-1b","cuda","fits","Q6_K",8192,2.75,20480,false,151.3,null,null],["nvidia-geforce-gtx-1660","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,268.6,null,null],["nvidia-geforce-gtx-1660","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","granite-4-1-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","granite-4-2-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-4-2-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-guardian-4-0-3b-toxicity-ja","cuda","tight","Q6_K",8192,4.67,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-guardian-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660","granite-vision-4-1-4b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660","harc-llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","harc-qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","hipo-1-7b","cuda","fits","IQ2_XXS",8192,2.82,8704,false,126,null,null],["nvidia-geforce-gtx-1660","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,48896,false,266.9,null,null],["nvidia-geforce-gtx-1660","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","holo-3-1-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660","holo-3-1-9b","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1660","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","holo2-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","holo2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","hunyuanocr","cuda","fits","Q6_K",8192,2.5,11776,false,153.9,null,null],["nvidia-geforce-gtx-1660","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1660","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-4b-baseline","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-4b-multiview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1660","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1660","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,"6",null],["nvidia-geforce-gtx-1660","januscoder-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","januscoderv-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1660","kanana-2-3b-base","cuda","tight","Q6_K",8192,4.89,null,null,null,null,null],["nvidia-geforce-gtx-1660","kanana-2-3b-instruct","cuda","tight","Q8_0",8192,5.65,null,null,null,null,null],["nvidia-geforce-gtx-1660","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1660","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1660","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1660","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1660","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"8",null],["nvidia-geforce-gtx-1660","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1660","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1660","lfm2-2-6b-exp","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1660","lfm2-2-6b-longevity","cuda","fits","IQ4_XS",8192,2.8,12288,false,123.9,null,null],["nvidia-geforce-gtx-1660","lfm2-2-6b-transcript","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1660","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","lfm2-5-1-2b-base","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-1-2b-instruct","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-1-2b-jp","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-1-2b-jp-202606","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-1-2b-thinking","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-2-6b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","lfm2-5-2-6b-base","cuda","fits","Q3_K_M",8192,2.74,15360,false,128.6,null,null],["nvidia-geforce-gtx-1660","lfm2-5-230m","cuda","fits","BF16",8192,1.83,82432,false,342.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","lfm2-5-350m","cuda","fits","BF16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1660","lfm2-5-8b-a1b","cuda","tight","Q5_K_M",8192,7.28,null,null,null,null,null],["nvidia-geforce-gtx-1660","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,94208,false,490.2,null,null],["nvidia-geforce-gtx-1660","lfm2-5-vl-1-6b","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-vl-1-6b-extract","cuda","fits","Q8_0",8192,2.6,27648,false,142.8,null,null],["nvidia-geforce-gtx-1660","lfm2-5-vl-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1660","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,65024,false,237.1,null,null],["nvidia-geforce-gtx-1660","lfm2-8b-a1b","cuda","tight","Q5_K_M",8192,7.18,null,null,null,null,null],["nvidia-geforce-gtx-1660","lfm2-vl-3b","cuda","fits","Q4_0",8192,2.86,8704,false,118.9,null,null],["nvidia-geforce-gtx-1660","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1660","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660","llama-3-2-1b-instruct","cuda","fits","Q8_0",8192,2.83,9472,false,121.4,null,null],["nvidia-geforce-gtx-1660","llama-3-2-3b-instruct","cuda","tight","Q8_0",8192,5.55,null,null,null,null,null],["nvidia-geforce-gtx-1660","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","mathform-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","medgemma-1-5-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,"6",null],["nvidia-geforce-gtx-1660","mellum2-12b-a2-5b-base","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","mellum2-12b-a2-5b-instruct","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1660","mellum2-12b-a2-5b-instruct-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","mellum2-12b-a2-5b-thinking","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1660","mellum2-12b-a2-5b-thinking-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","mimo-embodied-7b","cuda","tight","Q5_K_M",8192,7.42,null,null,null,null,null],["nvidia-geforce-gtx-1660","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-6-distill-qwen-9b","cuda","tight","Q5_K_M",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1660","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1660","minicpm-o-4-5","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","minicpm-v-4-6","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1660","minicpm-v-4-6-thinking","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1660","minicpm-v-4-7-1b","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1660","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1660","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1660","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,34560,false,207.9,null,null],["nvidia-geforce-gtx-1660","minicpm5-2b","cuda","fits","Q3_K_M",8192,2.68,12288,false,134,null,null],["nvidia-geforce-gtx-1660","minicpm5-2b-base","cuda","fits","Q3_K_M",8192,2.77,10240,false,126,null,null],["nvidia-geforce-gtx-1660","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-gtx-1660","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1660","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1660","ministral-3-3b-instruct-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1660","ministral-3-3b-reasoning-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1660","ministral-3-8b-instruct-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1660","ministral-3-8b-reasoning-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1660","mistral-7b-instruct-v0-2","cuda","tight","Q5_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1660","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1660","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","mistral-nemo-instruct-2407","cuda","tight","Q2_K",8192,7.07,null,null,null,null,null],["nvidia-geforce-gtx-1660","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1660","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1660","nemotron-3-content-safety","cuda","tight","Q6_K",8192,5.37,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nemotron-cascade-14b-thinking","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nemotron-cascade-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-cascade-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-orchestrator-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-terminal-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nemotron-terminal-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nouscoder-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-nano-4b-bf16","cuda","tight","Q8_0",8192,5.46,null,null,null,null,null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","nvidia-nemotron-nano-9b-v2","cuda","tight","Q4_K_M",8192,7.98,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-1-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-1-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.24,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","olmo-3-7b-instruct","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-instruct-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-instruct-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-rl-zero-general","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-rl-zero-if","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-rl-zero-mix","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-think","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-think-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmo-3-7b-think-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660","olmocr-2-7b-1025","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","phi-3-5-mini-instruct","cuda","tight","Q6_K",8192,7.43,null,null,null,null,null],["nvidia-geforce-gtx-1660","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1660","phi-4-mini-instruct","cuda","tight","Q8_0",8192,6.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1660","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen2-5-3b-instruct","cuda","fits","Q2_K",8192,2.86,8448,false,122.2,null,null],["nvidia-geforce-gtx-1660","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen2-5-coder-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen2-5-vl-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen2-5-vl-7b-surg-cholect50","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-0-6b","cuda","fits","Q8_0",8192,2.86,8192,false,122.1,null,null],["nvidia-geforce-gtx-1660","qwen3-1-7b","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-4b-instruct-2507","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-5-0-8b","cuda","fits","Q8_0",8192,2.48,36352,false,213,null,null],["nvidia-geforce-gtx-1660","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,48896,false,266.9,null,null],["nvidia-geforce-gtx-1660","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-5-2b","cuda","fits","Q4_0",8192,2.87,8192,false,147.2,null,null],["nvidia-geforce-gtx-1660","qwen3-5-2b-base","cuda","fits","Q4_0",8192,2.86,8960,false,148.3,null,null],["nvidia-geforce-gtx-1660","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"7",null],["nvidia-geforce-gtx-1660","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-5-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-5-4b-base","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-5-9b","cuda","tight","Q5_K_M",8192,7.74,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-5-9b-base","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8",null],["nvidia-geforce-gtx-1660","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,"5",null],["nvidia-geforce-gtx-1660","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-nemotron-14b-brrm","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-nemotron-8b-brrm","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1660","qwen3-vl-2b-instruct","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-vl-2b-thinking","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","qwen3-vl-4b-instruct","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-vl-4b-thinking","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-vl-8b-instruct","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwen3-vl-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","riva-translate-4b-instruct-v1-1","cuda","tight","Q6_K",8192,5.97,null,null,null,null,null],["nvidia-geforce-gtx-1660","rlvr-8b-0926","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","rnj-1-instruct","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","singguard-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","smollm3-3b","cuda","tight","BF16",8192,7.9,null,null,null,null,null],["nvidia-geforce-gtx-1660","smollm3-3b-gsm8k-sft","cuda","fits","IQ2_XXS",8192,2.78,9472,false,125.7,null,null],["nvidia-geforce-gtx-1660","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","spatial-ssrl-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","spatial-ssrl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1660","step3-vl-10b-base","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","tiny-aya-earth","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660","tiny-aya-fire","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660","tiny-aya-global","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660","tiny-aya-water","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660","translategemma-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1660","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","translategemma-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1660","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1660","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,"6",null],["nvidia-geforce-gtx-1660","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,"6",null],["nvidia-geforce-gtx-1660","trinity-nano-base","cuda","tight","Q6_K",8192,6.67,null,null,null,null,null],["nvidia-geforce-gtx-1660","trinity-nano-base-pre-anneal","cuda","tight","Q6_K",4096,6.43,null,null,null,null,null],["nvidia-geforce-gtx-1660","trinity-nano-preview","cuda","tight","Q8_0",8192,8.08,null,null,null,null,null],["nvidia-geforce-gtx-1660","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","ui-mate-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","ui-venus-1-5-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","ui-venus-1-5-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","ui-venus-2-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660","userrepgen-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660","webworld-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660","webworld-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660","x-reasoner-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","youtu-llm-2b","cuda","fits","Q4_K_M",8192,2.78,10496,false,125.5,null,null],["nvidia-geforce-gtx-1660","youtu-llm-2b-base","cuda","fits","Q4_K_M",8192,2.78,10496,false,125.5,null,null],["nvidia-geforce-gtx-1660","youtu-vl-4b-instruct","cuda","tight","Q6_K",8192,5.91,null,null,null,null,null],["nvidia-geforce-gtx-1660","zwz-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660","zwz-4b","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1660","zwz-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660","zwz-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","aescode-8b","cuda","tight","Q4_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","agentcpm-explore","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ai21-jamba-reasoning-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,228.2,null,null],["nvidia-geforce-gtx-1660-super","ai21-jamba2-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,228.2,null,null],["nvidia-geforce-gtx-1660-super","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","apertus-v1-1-1-5b","cuda","fits","Q8_0",4096,2.7,4096,false,231.1,null,null],["nvidia-geforce-gtx-1660-super","apertus-v1-1-1-5b-instruct","cuda","fits","Q8_0",4096,2.7,4096,false,231.1,null,null],["nvidia-geforce-gtx-1660-super","apertus-v1-1-4b","cuda","fits","IQ2_XXS",4096,2.72,4096,false,227.9,null,null],["nvidia-geforce-gtx-1660-super","apriel-1-6-15b-thinker","cuda","tight","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","aprielguard","cuda","tight","Q6_K",8192,7.87,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","astabrief-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","autoglm-phone-9b","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","autoglm-phone-9b-multilingual","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q5_K_M",8192,7.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","bitcpm-cann-3b-unquantized","cuda","fits","Q2_K",8192,2.86,8704,false,209.1,null,null],["nvidia-geforce-gtx-1660-super","caprl-qwen3vl-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","caprl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","contextpilot-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","contextpilot-e4b","cuda","tight","Q8_0",8192,6.65,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","cosmos-reason2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","d1-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","deepseek-r1-0528-qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","deepseek-r1-distill-llama-8b","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","deepseek-r1-distill-qwen-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","eurollm-9b-instruct-2512","cuda","tight","Q4_K_M",8192,7.84,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q3_K_M",8192,2.75,13056,false,685.3,null,null],["nvidia-geforce-gtx-1660-super","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","fara-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","fara1-5-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","fara1-5-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","frogmini-14b-2510","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","frognano-4b-2609","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,590.2,null,null],["nvidia-geforce-gtx-1660-super","gelab-zero-4b-preview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-2-9b-it","cuda","tight","IQ3_XXS",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-3-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-3-1b-it","cuda","fits","Q8_0",8192,2.68,32768,false,303.3,null,null],["nvidia-geforce-gtx-1660-super","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-3-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-4-12b-it","cuda","tight","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"8",null],["nvidia-geforce-gtx-1660-super","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","gemma-4-e2b","cuda","fits","Q3_K_M",8192,2.86,9728,false,255.4,null,null],["nvidia-geforce-gtx-1660-super","gemma-4-e2b-it","cuda","fits","Q3_K_M",8192,2.8,16896,false,267.4,null,null],["nvidia-geforce-gtx-1660-super","gemma-4-e4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","gemma-4-e4b-it","cuda","tight","Q8_0",8192,6.86,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","glm-4-6v-flash","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","granite-3-3-8b-instruct","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-4-0-1b","cuda","fits","Q3_K_M",8192,2.78,9216,false,219.9,null,null],["nvidia-geforce-gtx-1660-super","granite-4-0-350m","cuda","fits","BF16",8192,2.2,30464,false,357.5,null,null],["nvidia-geforce-gtx-1660-super","granite-4-0-h-1b","cuda","fits","Q6_K",8192,2.75,20480,false,264.8,null,null],["nvidia-geforce-gtx-1660-super","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,470,null,null],["nvidia-geforce-gtx-1660-super","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","granite-4-1-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","granite-4-2-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-4-2-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-guardian-4-0-3b-toxicity-ja","cuda","tight","Q6_K",8192,4.67,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-guardian-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","granite-vision-4-1-4b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","harc-llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","harc-qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","hipo-1-7b","cuda","fits","IQ2_XXS",8192,2.82,8704,false,220.5,null,null],["nvidia-geforce-gtx-1660-super","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,48896,false,467,null,null],["nvidia-geforce-gtx-1660-super","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","holo-3-1-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","holo-3-1-9b","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","holo2-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","holo2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","hunyuanocr","cuda","fits","Q6_K",8192,2.5,11776,false,269.3,null,null],["nvidia-geforce-gtx-1660-super","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-4b-baseline","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-4b-multiview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","januscoder-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","januscoderv-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","kanana-2-3b-base","cuda","tight","Q6_K",8192,4.89,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","kanana-2-3b-instruct","cuda","tight","Q8_0",8192,5.65,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"8",null],["nvidia-geforce-gtx-1660-super","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","lfm2-2-6b-exp","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-gtx-1660-super","lfm2-2-6b-longevity","cuda","fits","IQ4_XS",8192,2.8,12288,false,216.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-2-6b-transcript","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-gtx-1660-super","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","lfm2-5-1-2b-base","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-1-2b-instruct","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-1-2b-jp","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-1-2b-jp-202606","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-1-2b-thinking","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-2-6b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-2-6b-base","cuda","fits","Q3_K_M",8192,2.74,15360,false,225.1,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-230m","cuda","fits","BF16",8192,1.83,82432,false,599.8,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","lfm2-5-350m","cuda","fits","BF16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-8b-a1b","cuda","tight","Q5_K_M",8192,7.28,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,94208,false,857.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-vl-1-6b","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-vl-1-6b-extract","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-vl-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-gtx-1660-super","lfm2-8b-a1b","cuda","tight","Q5_K_M",8192,7.18,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","lfm2-vl-3b","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-gtx-1660-super","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","llama-3-2-1b-instruct","cuda","fits","Q8_0",8192,2.83,9472,false,212.4,null,null],["nvidia-geforce-gtx-1660-super","llama-3-2-3b-instruct","cuda","tight","Q8_0",8192,5.55,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","mathform-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","medgemma-1-5-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","mellum2-12b-a2-5b-base","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mellum2-12b-a2-5b-instruct","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mellum2-12b-a2-5b-instruct-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mellum2-12b-a2-5b-thinking","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mellum2-12b-a2-5b-thinking-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mimo-embodied-7b","cuda","tight","Q5_K_M",8192,7.42,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-6-distill-qwen-9b","cuda","tight","Q5_K_M",8192,8.03,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","minicpm-o-4-5","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","minicpm-v-4-6","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm-v-4-6-thinking","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm-v-4-7-1b","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-gtx-1660-super","minicpm5-2b","cuda","fits","Q3_K_M",8192,2.68,12288,false,234.5,null,null],["nvidia-geforce-gtx-1660-super","minicpm5-2b-base","cuda","fits","Q3_K_M",8192,2.77,10240,false,220.5,null,null],["nvidia-geforce-gtx-1660-super","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","ministral-3-3b-instruct-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ministral-3-3b-reasoning-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ministral-3-8b-instruct-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ministral-3-8b-reasoning-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mistral-7b-instruct-v0-2","cuda","tight","Q5_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","mistral-nemo-instruct-2407","cuda","tight","Q2_K",8192,7.07,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","nemotron-3-content-safety","cuda","tight","Q6_K",8192,5.37,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nemotron-cascade-14b-thinking","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nemotron-cascade-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-cascade-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-orchestrator-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-terminal-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nemotron-terminal-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nouscoder-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-nano-4b-bf16","cuda","tight","Q8_0",8192,5.46,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","nvidia-nemotron-nano-9b-v2","cuda","tight","Q4_K_M",8192,7.98,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-1-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-1-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.24,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-instruct","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-instruct-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-instruct-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-rl-zero-general","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-rl-zero-if","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-rl-zero-mix","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-think","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-think-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmo-3-7b-think-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","olmocr-2-7b-1025","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","phi-3-5-mini-instruct","cuda","tight","Q6_K",8192,7.43,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","phi-4-mini-instruct","cuda","tight","Q8_0",8192,6.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen2-5-3b-instruct","cuda","fits","Q2_K",8192,2.86,8448,false,213.9,null,null],["nvidia-geforce-gtx-1660-super","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen2-5-coder-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen2-5-vl-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen2-5-vl-7b-surg-cholect50","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-0-6b","cuda","fits","Q8_0",8192,2.86,8192,false,213.6,null,null],["nvidia-geforce-gtx-1660-super","qwen3-1-7b","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-4b-instruct-2507","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-0-8b","cuda","fits","Q8_0",8192,2.48,36352,false,372.7,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,48896,false,467,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-5-2b","cuda","fits","Q4_0",8192,2.87,8192,false,257.6,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-2b-base","cuda","fits","Q4_0",8192,2.86,8960,false,259.6,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"7",null],["nvidia-geforce-gtx-1660-super","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-5-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-4b-base","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-9b","cuda","tight","Q5_K_M",8192,7.74,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-5-9b-base","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8",null],["nvidia-geforce-gtx-1660-super","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,"5",null],["nvidia-geforce-gtx-1660-super","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-nemotron-14b-brrm","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-nemotron-8b-brrm","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","qwen3-vl-2b-instruct","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-vl-2b-thinking","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","qwen3-vl-4b-instruct","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-vl-4b-thinking","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-vl-8b-instruct","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwen3-vl-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","riva-translate-4b-instruct-v1-1","cuda","tight","Q6_K",8192,5.97,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","rlvr-8b-0926","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","rnj-1-instruct","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","singguard-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","smollm3-3b","cuda","tight","BF16",8192,7.9,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","smollm3-3b-gsm8k-sft","cuda","fits","IQ2_XXS",8192,2.78,9472,false,219.9,null,null],["nvidia-geforce-gtx-1660-super","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","spatial-ssrl-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","spatial-ssrl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","step3-vl-10b-base","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","tiny-aya-earth","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","tiny-aya-fire","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","tiny-aya-global","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","tiny-aya-water","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","translategemma-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","translategemma-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-gtx-1660-super","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,"6",null],["nvidia-geforce-gtx-1660-super","trinity-nano-base","cuda","tight","Q6_K",8192,6.67,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","trinity-nano-base-pre-anneal","cuda","tight","Q6_K",4096,6.43,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","trinity-nano-preview","cuda","tight","Q8_0",8192,8.08,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","ui-mate-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","ui-venus-1-5-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","ui-venus-1-5-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","ui-venus-2-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","userrepgen-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","webworld-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-gtx-1660-super","webworld-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","x-reasoner-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","youtu-llm-2b","cuda","fits","Q4_K_M",8192,2.78,10496,false,219.6,null,null],["nvidia-geforce-gtx-1660-super","youtu-llm-2b-base","cuda","fits","Q4_K_M",8192,2.78,10496,false,219.6,null,null],["nvidia-geforce-gtx-1660-super","youtu-vl-4b-instruct","cuda","tight","Q6_K",8192,5.91,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","zwz-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","zwz-4b","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","zwz-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-gtx-1660-super","zwz-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","aescode-8b","cuda","tight","Q4_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","agentcpm-explore","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ai21-jamba-reasoning-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,228.2,null,null],["nvidia-geforce-rtx-2060-6gb","ai21-jamba2-3b","cuda","fits","Q3_K_M",8192,2.76,45312,false,228.2,null,null],["nvidia-geforce-rtx-2060-6gb","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","apertus-v1-1-1-5b","cuda","fits","Q8_0",4096,2.7,4096,false,231.1,null,null],["nvidia-geforce-rtx-2060-6gb","apertus-v1-1-1-5b-instruct","cuda","fits","Q8_0",4096,2.7,4096,false,231.1,null,null],["nvidia-geforce-rtx-2060-6gb","apertus-v1-1-4b","cuda","fits","IQ2_XXS",4096,2.72,4096,false,227.9,null,null],["nvidia-geforce-rtx-2060-6gb","apriel-1-6-15b-thinker","cuda","tight","IQ2_M",8192,7.64,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","aprielguard","cuda","tight","Q6_K",8192,7.87,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","astabrief-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","autoglm-phone-9b","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","autoglm-phone-9b-multilingual","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","bielik-11b-v3-0-instruct","cuda","no","Q4_K_M",8192,9.44,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q5_K_M",8192,7.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","bitcpm-cann-3b-unquantized","cuda","fits","Q2_K",8192,2.86,8704,false,209.1,null,null],["nvidia-geforce-rtx-2060-6gb","caprl-qwen3vl-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","caprl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","contextpilot-14b","cuda","no","IQ2_M",8192,8.06,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","contextpilot-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","contextpilot-e4b","cuda","tight","Q8_0",8192,6.65,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","cosmos-reason2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","d1-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-0528-qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-distill-llama-8b","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-distill-qwen-14b","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","deepseek-r1-distill-qwen-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","eurollm-22b-2512","cuda","no","IQ2_XXS",8192,9.06,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","eurollm-9b-instruct-2512","cuda","tight","Q4_K_M",8192,7.84,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q3_K_M",8192,2.75,13056,false,685.3,null,null],["nvidia-geforce-rtx-2060-6gb","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","fara-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","fara1-5-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","fara1-5-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","frogmini-14b-2510","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","frognano-4b-2609","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,590.2,null,null],["nvidia-geforce-rtx-2060-6gb","gelab-zero-4b-preview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-2-9b-it","cuda","tight","IQ3_XXS",8192,8.03,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-3-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-3-1b-it","cuda","fits","Q8_0",8192,2.68,32768,false,303.3,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-3-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-4-12b-it","cuda","tight","Q3_K_M",8192,8.73,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"8",null],["nvidia-geforce-rtx-2060-6gb","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","gemma-4-e2b","cuda","fits","Q3_K_M",8192,2.86,9728,false,255.4,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-4-e2b-it","cuda","fits","Q3_K_M",8192,2.8,16896,false,267.4,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-4-e4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","gemma-4-e4b-it","cuda","tight","Q8_0",8192,6.86,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","glm-4-6v-flash","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","glm-4-7-flash-reap-23b-a3b","cuda","no","Q2_K",8192,10.25,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","granite-3-3-8b-instruct","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-0-1b","cuda","fits","Q3_K_M",8192,2.78,9216,false,219.9,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-0-350m","cuda","fits","BF16",8192,2.2,30464,false,357.5,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-0-h-1b","cuda","fits","Q6_K",8192,2.75,20480,false,264.8,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,470,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","granite-4-1-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","granite-4-2-3b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-4-2-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q4_K_M",8192,7.44,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-guardian-4-0-3b-toxicity-ja","cuda","tight","Q6_K",8192,4.67,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-guardian-4-1-8b","cuda","tight","Q4_K_M",8192,7.61,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","granite-vision-4-1-4b","cuda","tight","Q8_0",8192,5.48,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","harc-llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","harc-qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","hipo-1-7b","cuda","fits","IQ2_XXS",8192,2.82,8704,false,220.5,null,null],["nvidia-geforce-rtx-2060-6gb","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,48896,false,467,null,null],["nvidia-geforce-rtx-2060-6gb","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","holo-3-1-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","holo-3-1-9b","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","holo2-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","holo2-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","holo4-27b","cuda","no","IQ2_XXS",8192,10.5,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","hunyuanocr","cuda","fits","Q6_K",8192,2.5,11776,false,269.3,null,null],["nvidia-geforce-rtx-2060-6gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","januscoder-14b","cuda","no","Q2_K",8192,8.02,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","januscoder-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","januscoderv-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","kanana-2-3b-base","cuda","tight","Q6_K",8192,4.89,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","kanana-2-3b-instruct","cuda","tight","Q8_0",8192,5.65,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"8",null],["nvidia-geforce-rtx-2060-6gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","lfm2-2-6b-exp","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-2-6b-longevity","cuda","fits","IQ4_XS",8192,2.8,12288,false,216.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-2-6b-transcript","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-1-2b-base","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-1-2b-instruct","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-1-2b-jp","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-1-2b-jp-202606","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-1-2b-thinking","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-2-6b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-2-6b-base","cuda","fits","Q3_K_M",8192,2.74,15360,false,225.1,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-230m","cuda","fits","BF16",8192,1.83,82432,false,599.8,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-350m","cuda","fits","BF16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-8b-a1b","cuda","tight","Q5_K_M",8192,7.28,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,94208,false,857.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-vl-1-6b","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-vl-1-6b-extract","cuda","fits","Q8_0",8192,2.6,27648,false,249.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-vl-3b","cuda","tight","BF16",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,65024,false,414.9,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-8b-a1b","cuda","tight","Q5_K_M",8192,7.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","lfm2-vl-3b","cuda","fits","Q4_0",8192,2.86,8704,false,208.1,null,null],["nvidia-geforce-rtx-2060-6gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","llama-3-1-8b-instruct","cuda","tight","Q5_K_M",8192,7.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","llama-3-2-1b-instruct","cuda","fits","Q8_0",8192,2.83,9472,false,212.4,null,null],["nvidia-geforce-rtx-2060-6gb","llama-3-2-3b-instruct","cuda","tight","Q8_0",8192,5.55,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","mathform-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","medgemma-1-5-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mellum2-1-12b-a2-5b-thinking","cuda","no","Q4_K_M",8192,9.38,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","mellum2-12b-a2-5b-base","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mellum2-12b-a2-5b-instruct","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mellum2-12b-a2-5b-instruct-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mellum2-12b-a2-5b-thinking","cuda","tight","Q3_K_M",8192,7.56,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mellum2-12b-a2-5b-thinking-sft","cuda","tight","IQ4_XS",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mimo-embodied-7b","cuda","tight","Q5_K_M",8192,7.42,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-6-distill-qwen-9b","cuda","tight","Q5_K_M",8192,8.03,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","minicpm-o-4-5","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm-v-4-6","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm-v-4-6-thinking","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm-v-4-7-1b","cuda","fits","Q8_0",8192,2.48,36352,false,372.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,34560,false,363.8,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm5-2b","cuda","fits","Q3_K_M",8192,2.68,12288,false,234.5,null,null],["nvidia-geforce-rtx-2060-6gb","minicpm5-2b-base","cuda","fits","Q3_K_M",8192,2.77,10240,false,220.5,null,null],["nvidia-geforce-rtx-2060-6gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","ministral-3-3b-instruct-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ministral-3-3b-reasoning-2512","cuda","tight","Q8_0",8192,5.71,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ministral-3-8b-instruct-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ministral-3-8b-reasoning-2512","cuda","tight","Q4_K_M",8192,7.19,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mistral-7b-instruct-v0-2","cuda","tight","Q5_K_M",8192,7.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","mistral-nemo-instruct-2407","cuda","tight","Q2_K",8192,7.07,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","muse-glimmer-30b","cuda","no","IQ2_XXS",8192,10.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","nemotron-3-content-safety","cuda","tight","Q6_K",8192,5.37,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nemotron-cascade-14b-thinking","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nemotron-cascade-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-cascade-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-orchestrator-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-terminal-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nemotron-terminal-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nouscoder-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-nano-4b-bf16","cuda","tight","Q8_0",8192,5.46,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","nvidia-nemotron-nano-9b-v2","cuda","tight","Q4_K_M",8192,7.98,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.24,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-instruct","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-instruct-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-instruct-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-rl-zero-code","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-rl-zero-general","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-rl-zero-if","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-rl-zero-math","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-rl-zero-mix","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-think","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-think-dpo","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmo-3-7b-think-sft","cuda","tight","IQ4_XS",8192,9.21,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","olmocr-2-7b-1025","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","phi-3-5-mini-instruct","cuda","tight","Q6_K",8192,7.43,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","phi-4","cuda","no","Q2_K",8192,8.25,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","phi-4-mini-instruct","cuda","tight","Q8_0",8192,6.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-14b-instruct","cuda","no","Q2_K",8192,8.3,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-3b-instruct","cuda","fits","Q2_K",8192,2.86,8448,false,213.9,null,null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-coder-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-vl-7b-instruct","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen2-5-vl-7b-surg-cholect50","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-0-6b","cuda","fits","Q8_0",8192,2.86,8192,false,213.6,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-1-7b","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-4b-instruct-2507","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-0-8b","cuda","fits","Q8_0",8192,2.48,36352,false,372.7,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,48896,false,467,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-2b","cuda","fits","Q4_0",8192,2.87,8192,false,257.6,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-2b-base","cuda","fits","Q4_0",8192,2.86,8960,false,259.6,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"7",null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-4b","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-4b-base","cuda","tight","Q8_0",8192,6.37,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-9b","cuda","tight","Q5_K_M",8192,7.74,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-5-9b-base","cuda","tight","Q5_K_M",8192,7.63,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"8",null],["nvidia-geforce-rtx-2060-6gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-8-27b","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-8-3-6-27b-blend","cuda","no","IQ2_XXS",8192,10.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-reap-25b-a3b","cuda","no","IQ2_XXS",8192,8.11,null,null,null,"5",null],["nvidia-geforce-rtx-2060-6gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-nemotron-14b-brrm","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-nemotron-8b-brrm","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-2b-instruct","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-2b-thinking","cuda","tight","BF16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-4b-instruct","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-4b-thinking","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-8b-instruct","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwen3-vl-8b-thinking","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","riva-translate-4b-instruct-v1-1","cuda","tight","Q6_K",8192,5.97,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","rlvr-8b-0926","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","rnj-1-instruct","cuda","tight","Q4_K_M",8192,7.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","singguard-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","smollm3-3b","cuda","tight","BF16",8192,7.9,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","smollm3-3b-gsm8k-sft","cuda","fits","IQ2_XXS",8192,2.78,9472,false,219.9,null,null],["nvidia-geforce-rtx-2060-6gb","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","spatial-ssrl-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","spatial-ssrl-qwen3vl-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","step3-vl-10b-base","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","tiny-aya-earth","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","tiny-aya-fire","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","tiny-aya-global","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","tiny-aya-water","cuda","tight","Q8_0",8192,5.64,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","translategemma-12b-it","cuda","tight","Q2_K",8192,8.23,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","translategemma-4b-it","cuda","tight","Q8_0",8192,6.3,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-6gb","trinity-mini","cuda","no","IQ2_XXS",8192,8.25,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","trinity-mini-base","cuda","no","IQ2_XXS",8192,8.69,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","trinity-mini-base-pre-anneal","cuda","no","IQ2_XXS",4096,8.41,null,null,null,"6",null],["nvidia-geforce-rtx-2060-6gb","trinity-nano-base","cuda","tight","Q6_K",8192,6.67,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","trinity-nano-base-pre-anneal","cuda","tight","Q6_K",4096,6.43,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","trinity-nano-preview","cuda","tight","Q8_0",8192,8.08,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","ui-mate-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","ui-venus-1-5-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","ui-venus-1-5-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","ui-venus-2-9b","cuda","tight","Q5_K_M",8192,8.01,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","userrepgen-4b","cuda","tight","Q8_0",8192,6.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","webworld-14b","cuda","tight","IQ2_M",8192,7.52,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-6gb","webworld-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","x-reasoner-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","youtu-llm-2b","cuda","fits","Q4_K_M",8192,2.78,10496,false,219.6,null,null],["nvidia-geforce-rtx-2060-6gb","youtu-llm-2b-base","cuda","fits","Q4_K_M",8192,2.78,10496,false,219.6,null,null],["nvidia-geforce-rtx-2060-6gb","youtu-vl-4b-instruct","cuda","tight","Q6_K",8192,5.91,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","zwz-2b","cuda","tight","F16",8192,5.62,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","zwz-4b","cuda","tight","Q6_K",8192,5.74,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","zwz-7b","cuda","tight","Q6_K",8192,7.47,null,null,null,null,null],["nvidia-geforce-rtx-2060-6gb","zwz-8b","cuda","tight","Q5_K_M",8192,7.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2060-super","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2060-super","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2060-super","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2060-super","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-2060-super","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,129,null,null],["nvidia-geforce-rtx-2060-super","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,125.7,null,null],["nvidia-geforce-rtx-2060-super","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,145.8,null,null],["nvidia-geforce-rtx-2060-super","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,156,null,null],["nvidia-geforce-rtx-2060-super","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,143.2,null,null],["nvidia-geforce-rtx-2060-super","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2060-super","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2060-super","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-2060-super","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,142.6,null,null],["nvidia-geforce-rtx-2060-super","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2060-super","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-2060-super","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-2060-super","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2060-super","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-2060-super","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,172.7,null,null],["nvidia-geforce-rtx-2060-super","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,141.7,null,null],["nvidia-geforce-rtx-2060-super","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,140.9,null,null],["nvidia-geforce-rtx-2060-super","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,186.3,null,null],["nvidia-geforce-rtx-2060-super","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-2060-super","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,149.7,null,null],["nvidia-geforce-rtx-2060-super","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-2060-super","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2060-super","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2060-super","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2060-super","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2060-super","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,136.1,null,null],["nvidia-geforce-rtx-2060-super","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,190.5,null,null],["nvidia-geforce-rtx-2060-super","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2060-super","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2060-super","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,237.9,null,null],["nvidia-geforce-rtx-2060-super","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2060-super","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2060-super","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2060-super","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2060-super","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2060-super","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,149.3,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,190.8,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2060-super","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2060-super","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2060-super","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,163.5,null,null],["nvidia-geforce-rtx-2060-super","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,125.3,null,null],["nvidia-geforce-rtx-2060-super","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2060-super","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,134.1,null,null],["nvidia-geforce-rtx-2060-super","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2060-super","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2060-super","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2060-super","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2060-super","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2060-super","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2060-super","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,163.3,null,null],["nvidia-geforce-rtx-2060-super","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,203.8,null,null],["nvidia-geforce-rtx-2060-super","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2060-super","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2060-super","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,127.4,null,null],["nvidia-geforce-rtx-2060-super","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2060-super","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-2060-super","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,150.5,null,null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,140.7,null,null],["nvidia-geforce-rtx-2060-super","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,125.1,null,null],["nvidia-geforce-rtx-2060-super","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2060-super","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2060-super","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2060-super","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2060-super","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,210.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,278.9,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,213.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,272.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-2060-super","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,149.4,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-2060-super","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-2060-super","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-2060-super","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,124.3,null,null],["nvidia-geforce-rtx-2060-super","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2060-super","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2060-super","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2060-super","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2060-super","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2060-super","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2060-super","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2060-super","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2060-super","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2060-super","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,647.1,null,null],["nvidia-geforce-rtx-2060-super","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,669.8,null,null],["nvidia-geforce-rtx-2060-super","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,624.3,null,null],["nvidia-geforce-rtx-2060-super","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-2060-super","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2060-super","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2060-super","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2060-super","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2060-super","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2060-super","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2060-super","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,134.7,null,null],["nvidia-geforce-rtx-2060-super","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2060-super","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2060-super","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2060-super","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-2070","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-2070","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2070","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2070","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-2070","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2070","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2070","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-2070","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,129,null,null],["nvidia-geforce-rtx-2070","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-2070","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,125.7,null,null],["nvidia-geforce-rtx-2070","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-2070","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-2070","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,145.8,null,null],["nvidia-geforce-rtx-2070","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,156,null,null],["nvidia-geforce-rtx-2070","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-2070","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-2070","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,143.2,null,null],["nvidia-geforce-rtx-2070","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2070","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2070","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-2070","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2070","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2070","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2070","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2070","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-2070","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-2070","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-2070","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2070","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-2070","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-2070","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-2070","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-2070","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-2070","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-2070","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,142.6,null,null],["nvidia-geforce-rtx-2070","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2070","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2070","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2070","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-2070","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-2070","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-2070","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2070","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-2070","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2070","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2070","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-2070","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-2070","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-2070","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-2070","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-2070","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-2070","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-2070","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,172.7,null,null],["nvidia-geforce-rtx-2070","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,141.7,null,null],["nvidia-geforce-rtx-2070","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,140.9,null,null],["nvidia-geforce-rtx-2070","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-2070","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-2070","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-2070","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-2070","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2070","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,186.3,null,null],["nvidia-geforce-rtx-2070","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-2070","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,149.7,null,null],["nvidia-geforce-rtx-2070","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-2070","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2070","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2070","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2070","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2070","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2070","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2070","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2070","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2070","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2070","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2070","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,136.1,null,null],["nvidia-geforce-rtx-2070","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-2070","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,190.5,null,null],["nvidia-geforce-rtx-2070","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2070","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2070","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2070","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2070","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2070","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-2070","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-2070","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2070","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,237.9,null,null],["nvidia-geforce-rtx-2070","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-2070","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-2070","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2070","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-2070","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-2070","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2070","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2070","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-2070","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-2070","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-2070","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-2070","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-2070","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-2070","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-2070","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-2070","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-2070","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2070","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2070","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2070","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2070","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-2070","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,149.3,null,null],["nvidia-geforce-rtx-2070","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,190.8,null,null],["nvidia-geforce-rtx-2070","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-2070","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-2070","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2070","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-2070","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-2070","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2070","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2070","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2070","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2070","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-2070","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2070","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-2070","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-2070","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-2070","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,163.5,null,null],["nvidia-geforce-rtx-2070","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,125.3,null,null],["nvidia-geforce-rtx-2070","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2070","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2070","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2070","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2070","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2070","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2070","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2070","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,134.1,null,null],["nvidia-geforce-rtx-2070","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2070","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-2070","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2070","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2070","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2070","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-2070","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2070","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2070","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2070","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,163.3,null,null],["nvidia-geforce-rtx-2070","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,203.8,null,null],["nvidia-geforce-rtx-2070","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2070","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2070","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2070","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2070","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2070","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2070","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2070","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2070","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2070","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,127.4,null,null],["nvidia-geforce-rtx-2070","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-2070","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-2070","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2070","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-2070","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-2070","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2070","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-2070","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-2070","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2070","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-2070","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,150.5,null,null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2070","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2070","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2070","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2070","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2070","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2070","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2070","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2070","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2070","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-2070","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-2070","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-2070","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,140.7,null,null],["nvidia-geforce-rtx-2070","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2070","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,125.1,null,null],["nvidia-geforce-rtx-2070","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2070","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2070","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2070","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2070","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2070","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,210.2,null,null],["nvidia-geforce-rtx-2070","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-2070","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-2070","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2070","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-2070","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,278.9,null,null],["nvidia-geforce-rtx-2070","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2070","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-2070","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,213.2,null,null],["nvidia-geforce-rtx-2070","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,272.2,null,null],["nvidia-geforce-rtx-2070","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-2070","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-2070","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,149.4,null,null],["nvidia-geforce-rtx-2070","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2070","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-2070","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-2070","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2070","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-2070","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2070","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2070","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2070","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2070","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-2070","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,124.3,null,null],["nvidia-geforce-rtx-2070","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-2070","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2070","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2070","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2070","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2070","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-2070","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2070","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2070","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2070","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2070","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2070","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2070","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2070","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2070","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-2070","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2070","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-2070","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-2070","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-2070","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,647.1,null,null],["nvidia-geforce-rtx-2070","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,669.8,null,null],["nvidia-geforce-rtx-2070","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,624.3,null,null],["nvidia-geforce-rtx-2070","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-2070","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2070","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-2070","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2070","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2070","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2070","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2070","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2070","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2070","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2070","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2070","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2070","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,134.7,null,null],["nvidia-geforce-rtx-2070","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2070","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2070","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2070","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-2080","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-2080","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2080","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-2080","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-2080","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2080","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-2080","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-2080","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,129,null,null],["nvidia-geforce-rtx-2080","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-2080","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,125.7,null,null],["nvidia-geforce-rtx-2080","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-2080","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-2080","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,145.8,null,null],["nvidia-geforce-rtx-2080","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,156,null,null],["nvidia-geforce-rtx-2080","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-2080","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-2080","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,143.2,null,null],["nvidia-geforce-rtx-2080","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2080","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2080","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-2080","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2080","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2080","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2080","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2080","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-2080","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-2080","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-2080","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2080","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-2080","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-2080","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-2080","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-2080","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-2080","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-2080","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,142.6,null,null],["nvidia-geforce-rtx-2080","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2080","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2080","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2080","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-2080","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-2080","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-2080","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2080","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-2080","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2080","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2080","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-2080","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-2080","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-2080","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-2080","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-2080","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-2080","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-2080","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,172.7,null,null],["nvidia-geforce-rtx-2080","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,141.7,null,null],["nvidia-geforce-rtx-2080","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,140.9,null,null],["nvidia-geforce-rtx-2080","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-2080","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-2080","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-2080","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-2080","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2080","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,186.3,null,null],["nvidia-geforce-rtx-2080","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-2080","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,149.7,null,null],["nvidia-geforce-rtx-2080","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-2080","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2080","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2080","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2080","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-2080","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2080","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2080","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-2080","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2080","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-2080","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-2080","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,136.1,null,null],["nvidia-geforce-rtx-2080","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-2080","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,190.5,null,null],["nvidia-geforce-rtx-2080","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2080","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2080","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2080","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2080","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-2080","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-2080","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-2080","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2080","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,237.9,null,null],["nvidia-geforce-rtx-2080","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-2080","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-2080","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2080","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-2080","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-2080","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2080","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-2080","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-2080","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-2080","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-2080","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-2080","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-2080","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-2080","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-2080","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-2080","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-2080","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-2080","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2080","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2080","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2080","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-2080","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,149.3,null,null],["nvidia-geforce-rtx-2080","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,190.8,null,null],["nvidia-geforce-rtx-2080","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-2080","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-2080","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2080","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-2080","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-2080","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-2080","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-2080","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2080","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-2080","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-2080","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-2080","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-2080","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-2080","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-2080","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,163.5,null,null],["nvidia-geforce-rtx-2080","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,125.3,null,null],["nvidia-geforce-rtx-2080","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2080","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2080","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2080","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2080","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2080","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-2080","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-2080","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,134.1,null,null],["nvidia-geforce-rtx-2080","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2080","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-2080","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2080","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2080","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-2080","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-2080","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2080","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2080","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-2080","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,163.3,null,null],["nvidia-geforce-rtx-2080","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,203.8,null,null],["nvidia-geforce-rtx-2080","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2080","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2080","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-2080","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2080","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-2080","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2080","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-2080","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2080","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-2080","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,127.4,null,null],["nvidia-geforce-rtx-2080","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-2080","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-2080","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-2080","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-2080","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-2080","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2080","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-2080","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-2080","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2080","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-2080","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,150.5,null,null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-2080","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2080","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2080","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2080","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2080","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-2080","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2080","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-2080","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-2080","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-2080","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-2080","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-2080","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,140.7,null,null],["nvidia-geforce-rtx-2080","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2080","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,125.1,null,null],["nvidia-geforce-rtx-2080","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2080","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-2080","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2080","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2080","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-2080","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,210.2,null,null],["nvidia-geforce-rtx-2080","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-2080","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-2080","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2080","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-2080","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,278.9,null,null],["nvidia-geforce-rtx-2080","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-2080","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-2080","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,213.2,null,null],["nvidia-geforce-rtx-2080","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,272.2,null,null],["nvidia-geforce-rtx-2080","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-2080","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-2080","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,149.4,null,null],["nvidia-geforce-rtx-2080","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-2080","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-2080","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-2080","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2080","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-2080","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-2080","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2080","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2080","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-2080","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-2080","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,124.3,null,null],["nvidia-geforce-rtx-2080","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-2080","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2080","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2080","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-2080","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-2080","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2080","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2080","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2080","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-2080","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-2080","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-2080","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-2080","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-2080","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-2080","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-2080","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-2080","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,647.1,null,null],["nvidia-geforce-rtx-2080","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,669.8,null,null],["nvidia-geforce-rtx-2080","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,624.3,null,null],["nvidia-geforce-rtx-2080","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-2080","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2080","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-2080","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-2080","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-2080","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-2080","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-2080","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-2080","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-2080","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2080","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-2080","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,134.7,null,null],["nvidia-geforce-rtx-2080","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-2080","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-2080","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-2080","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-2080-ti","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","aescode-8b","cuda","fits","Q4_K_M",8192,7.27,12288,false,101.6,null,null],["nvidia-geforce-rtx-2080-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,22528,false,136.6,null,null],["nvidia-geforce-rtx-2080-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,207872,false,101.4,null,null],["nvidia-geforce-rtx-2080-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,207872,false,101.4,null,null],["nvidia-geforce-rtx-2080-ti","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,235.3,null,null],["nvidia-geforce-rtx-2080-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,235.3,null,null],["nvidia-geforce-rtx-2080-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,191.8,null,null],["nvidia-geforce-rtx-2080-ti","apriel-1-6-15b-thinker","cuda","fits","IQ2_M",8192,7.64,9216,false,95,null,null],["nvidia-geforce-rtx-2080-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,8192,false,91.6,null,null],["nvidia-geforce-rtx-2080-ti","armorocr","cuda","fits","Q4_K_M",8192,7.09,13568,false,104.8,null,null],["nvidia-geforce-rtx-2080-ti","astabrief-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","autoglm-phone-9b","cuda","fits","Q4_K_M",8192,7.34,20736,false,100.3,null,null],["nvidia-geforce-rtx-2080-ti","autoglm-phone-9b-multilingual","cuda","fits","Q4_K_M",8192,7.34,20736,false,100.3,null,null],["nvidia-geforce-rtx-2080-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","bielik-11b-v3-0-instruct","cuda","tight","Q6_K",8192,11.8,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q5_K_M",8192,7.7,9216,false,94.1,null,null],["nvidia-geforce-rtx-2080-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,200.5,null,null],["nvidia-geforce-rtx-2080-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","contextpilot-14b","cuda","tight","Q5_K_M",8192,12.65,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","contextpilot-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,76032,false,120.4,null,null],["nvidia-geforce-rtx-2080-ti","cosmos-reason2-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","cosmos-reason2-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,111.4,null,null],["nvidia-geforce-rtx-2080-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-distill-llama-8b","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-distill-qwen-14b","cuda","tight","Q5_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","devstral-small-2-24b-instruct-2512","cuda","tight","Q3_K_M",8192,13.55,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","eurollm-22b-2512","cuda","tight","Q3_K_M",8192,13.62,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","eurollm-22b-instruct-2512","cuda","tight","Q3_K_M",8192,13.62,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","eurollm-9b-instruct-2512","cuda","fits","Q4_K_M",8192,7.84,8192,false,92,null,null],["nvidia-geforce-rtx-2080-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1002.2,null,null],["nvidia-geforce-rtx-2080-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","fara-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","fara1-5-27b","cuda","tight","Q2_K",8192,13.61,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,51968,false,129.6,null,null],["nvidia-geforce-rtx-2080-ti","fara1-5-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,110.1,null,null],["nvidia-geforce-rtx-2080-ti","frogboss-32b-2510","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","frogmini-14b-2510","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,51968,false,129.6,null,null],["nvidia-geforce-rtx-2080-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1082,null,null],["nvidia-geforce-rtx-2080-ti","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","gemma-2-27b-it","cuda","tight","IQ2_M",8192,13.78,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-2-9b-it","cuda","fits","IQ2_M",8192,7.67,8192,false,111.1,null,null],["nvidia-geforce-rtx-2080-ti","gemma-3-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,301.2,null,null],["nvidia-geforce-rtx-2080-ti","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,139.6,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","gemma-4-12b-it","cuda","tight","Q6_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-26b-a4b-it","cuda","tight","Q2_K",8192,13.36,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,314.4,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,132.3,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,72960,false,119,null,null],["nvidia-geforce-rtx-2080-ti","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,64000,false,115.4,null,null],["nvidia-geforce-rtx-2080-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8",null],["nvidia-geforce-rtx-2080-ti","glm-4-6v-flash","cuda","fits","Q4_K_M",8192,7.34,20736,false,100.3,null,null],["nvidia-geforce-rtx-2080-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q3_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","granite-3-3-8b-instruct","cuda","fits","Q4_K_M",8192,7.44,10752,false,98,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,41216,false,156.5,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,655.5,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,205.9,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,861.6,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"2",null],["nvidia-geforce-rtx-2080-ti","granite-4-1-3b","cuda","fits","Q8_0",8192,5.48,37120,false,143.7,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-1-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,95.4,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"2",null],["nvidia-geforce-rtx-2080-ti","granite-4-2-3b","cuda","fits","Q8_0",8192,5.48,37120,false,143.7,null,null],["nvidia-geforce-rtx-2080-ti","granite-4-2-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,95.4,null,null],["nvidia-geforce-rtx-2080-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q4_K_M",8192,7.44,10752,false,98,null,null],["nvidia-geforce-rtx-2080-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,46848,false,177.9,null,null],["nvidia-geforce-rtx-2080-ti","granite-guardian-4-1-8b","cuda","fits","Q4_K_M",8192,7.61,9728,false,95.4,null,null],["nvidia-geforce-rtx-2080-ti","granite-vision-4-1-4b","cuda","fits","Q8_0",8192,5.48,37120,false,143.7,null,null],["nvidia-geforce-rtx-2080-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,262,null,null],["nvidia-geforce-rtx-2080-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,856.2,null,null],["nvidia-geforce-rtx-2080-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,52224,false,130,null,null],["nvidia-geforce-rtx-2080-ti","holo-3-1-9b","cuda","fits","Q5_K_M",8192,7.63,15360,false,102.2,null,null],["nvidia-geforce-rtx-2080-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","holo2-4b","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","holo2-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","holo4-27b","cuda","tight","IQ3_XXS",8192,13.08,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","holo4-35b-a3b","cuda","tight","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,327.1,null,null],["nvidia-geforce-rtx-2080-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","ising-calibration-1-35b-a3b","cuda","tight","IQ2_M",8192,13.14,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","januscoder-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","januscoder-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,30976,false,167.2,null,null],["nvidia-geforce-rtx-2080-ti","kanana-2-3b-instruct","cuda","fits","Q8_0",8192,5.65,25088,false,138.3,null,null],["nvidia-geforce-rtx-2080-ti","kat-coder-v2-5-dev","cuda","tight","IQ2_M",8192,13.54,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ2_M",8192,12.81,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,86784,false,116.8,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,86784,false,116.8,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,86784,false,116.8,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,72960,false,111.4,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,262.4,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1099.7,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,760.7,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-8b-a1b","cuda","fits","Q5_K_M",8192,7.28,50176,false,465.4,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1572.8,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,252.3,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,111.4,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,760.7,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,760.7,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-8b-a1b","cuda","fits","Q5_K_M",8192,7.18,57600,false,505.5,null,null],["nvidia-geforce-rtx-2080-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,86784,false,116.8,null,null],["nvidia-geforce-rtx-2080-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","llama-3-1-8b-instruct","cuda","fits","Q5_K_M",8192,7.59,10240,false,95.7,null,null],["nvidia-geforce-rtx-2080-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,122624,false,224.8,null,null],["nvidia-geforce-rtx-2080-ti","llama-3-2-3b-instruct","cuda","fits","Q8_0",8192,5.55,28416,false,141.5,null,null],["nvidia-geforce-rtx-2080-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8",null],["nvidia-geforce-rtx-2080-ti","mathform-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,139.6,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q6_K",8192,12.08,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-12b-a2-5b-base","cuda","fits","Q3_K_M",8192,7.7,18688,false,447.7,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q3_K_M",8192,7.56,27904,false,429.3,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q3_K_M",8192,7.7,18688,false,447.7,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q3_K_M",8192,7.56,27904,false,429.3,null,null],["nvidia-geforce-rtx-2080-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q3_K_M",8192,7.7,18688,false,447.7,null,null],["nvidia-geforce-rtx-2080-ti","mimo-embodied-7b","cuda","fits","Q5_K_M",8192,7.42,11264,false,99,null,null],["nvidia-geforce-rtx-2080-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","Q4_K_M",8192,7.14,29696,false,111.5,null,null],["nvidia-geforce-rtx-2080-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","minicpm-o-4-5","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,383.6,null,null],["nvidia-geforce-rtx-2080-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,383.6,null,null],["nvidia-geforce-rtx-2080-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,383.6,null,null],["nvidia-geforce-rtx-2080-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,667,null,null],["nvidia-geforce-rtx-2080-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,667,null,null],["nvidia-geforce-rtx-2080-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,667,null,null],["nvidia-geforce-rtx-2080-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,49664,false,127,null,null],["nvidia-geforce-rtx-2080-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,108544,false,280.2,null,null],["nvidia-geforce-rtx-2080-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"7",null],["nvidia-geforce-rtx-2080-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ministral-3-3b-instruct-2512","cuda","fits","Q8_0",8192,5.71,28416,false,136.4,null,null],["nvidia-geforce-rtx-2080-ti","ministral-3-3b-reasoning-2512","cuda","fits","Q8_0",8192,5.71,28416,false,136.4,null,null],["nvidia-geforce-rtx-2080-ti","ministral-3-8b-instruct-2512","cuda","fits","Q4_K_M",8192,7.19,13056,false,102.2,null,null],["nvidia-geforce-rtx-2080-ti","ministral-3-8b-reasoning-2512","cuda","fits","Q4_K_M",8192,7.19,13056,false,102.2,null,null],["nvidia-geforce-rtx-2080-ti","mistral-7b-instruct-v0-2","cuda","fits","Q5_K_M",8192,7.27,12544,false,100.7,null,null],["nvidia-geforce-rtx-2080-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","mistral-nemo-instruct-2407","cuda","fits","Q2_K",8192,7.07,13056,false,104.3,null,null],["nvidia-geforce-rtx-2080-ti","mistral-small-3-2-24b-instruct-2506","cuda","tight","Q3_K_M",8192,13.55,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8",null],["nvidia-geforce-rtx-2080-ti","muse-glimmer-30b","cuda","tight","IQ3_XXS",8192,12.61,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,121344,false,177.3,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","nemotron-cascade-14b-thinking","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","nemotron-cascade-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-cascade-8b-thinking","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-orchestrator-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-terminal-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-terminal-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","nemotron-terminal-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","north-mini-code-1-0","cuda","tight","Q2_K",8192,13.23,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","nouscoder-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q8_0",8192,5.46,141824,false,157,null,null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","Q4_0",8192,6.88,62976,false,120,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-1-7b-rl-zero-math","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-1125-32b","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","olmo-3-32b-think-dpo","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-32b-think-sft","cuda","tight","IQ2_M",8192,13.93,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-instruct","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-instruct-dpo","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-instruct-sft","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-rl-zero-code","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-rl-zero-general","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-rl-zero-if","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-rl-zero-math","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-rl-zero-mix","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-think","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-think-dpo","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmo-3-7b-think-sft","cuda","fits","IQ2_XXS",8192,7.47,8960,false,131.4,null,null],["nvidia-geforce-rtx-2080-ti","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","phi-3-5-mini-instruct","cuda","fits","Q6_K",8192,7.43,9216,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","phi-4","cuda","tight","Q5_K_M",8192,12.78,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,18944,false,119.6,null,null],["nvidia-geforce-rtx-2080-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-rtx-2080-ti","qwen2-5-14b-instruct","cuda","tight","Q5_K_M",8192,12.67,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,172,null,null],["nvidia-geforce-rtx-2080-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,289,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,383.5,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,856.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-rtx-2080-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,185344,false,159.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,374.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen3-5-35b-a3b-base","cuda","tight","IQ2_M",8192,13.02,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,52224,false,130,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,52224,false,130,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-9b","cuda","fits","Q5_K_M",8192,7.74,12032,false,100.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-5-9b-base","cuda","fits","Q5_K_M",8192,7.63,15360,false,102.2,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen3-6-35b-a3b","cuda","tight","IQ2_M",8192,13.54,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","qwen3-8-27b","cuda","tight","IQ3_XXS",8192,13.79,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-8-3-6-27b-blend","cuda","tight","IQ3_XXS",8192,13.79,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-reap-25b-a3b","cuda","tight","Q3_K_M",8192,13.26,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","qwen3-nemotron-14b-brrm","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-8b-instruct","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","qwen3-vl-8b-thinking","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"4",null],["nvidia-geforce-rtx-2080-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,128.6,null,null],["nvidia-geforce-rtx-2080-ti","rlvr-8b-0926","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","rnj-1-instruct","cuda","fits","Q4_K_M",8192,7.34,12288,false,99.7,null,null],["nvidia-geforce-rtx-2080-ti","sera-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","singguard-2b","cuda","fits","F16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","smollm3-3b","cuda","fits","Q8_0",8192,5.08,45824,false,159.1,null,null],["nvidia-geforce-rtx-2080-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,55552,false,197,null,null],["nvidia-geforce-rtx-2080-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-rtx-2080-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,16128,false,112.4,null,null],["nvidia-geforce-rtx-2080-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"6",null],["nvidia-geforce-rtx-2080-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"7",null],["nvidia-geforce-rtx-2080-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","step3-vl-10b-base","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","tiny-aya-earth","cuda","fits","Q8_0",8192,5.64,94976,false,156.5,null,null],["nvidia-geforce-rtx-2080-ti","tiny-aya-fire","cuda","fits","Q8_0",8192,5.64,94976,false,156.5,null,null],["nvidia-geforce-rtx-2080-ti","tiny-aya-global","cuda","fits","Q8_0",8192,5.64,94976,false,156.5,null,null],["nvidia-geforce-rtx-2080-ti","tiny-aya-water","cuda","fits","Q8_0",8192,5.64,94976,false,156.5,null,null],["nvidia-geforce-rtx-2080-ti","translategemma-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,79616,false,139.6,null,null],["nvidia-geforce-rtx-2080-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-2080-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-2080-ti","trinity-mini","cuda","tight","Q3_K_M",8192,13.65,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","trinity-mini-base","cuda","tight","IQ3_XXS",8192,11.76,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","trinity-mini-base-pre-anneal","cuda","tight","Q3_K_M",4096,13.8,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,81408,false,684,null,null],["nvidia-geforce-rtx-2080-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,731.7,null,null],["nvidia-geforce-rtx-2080-ti","trinity-nano-preview","cuda","fits","Q6_K",8192,6.69,80640,false,673.6,null,null],["nvidia-geforce-rtx-2080-ti","ui-mate-27b","cuda","tight","Q2_K",8192,13.61,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ui-mate-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,110.1,null,null],["nvidia-geforce-rtx-2080-ti","ui-mate-democua-27b","cuda","tight","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","ui-venus-1-5-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","ui-venus-2-9b","cuda","fits","Q4_K_M",8192,7.21,27648,false,110.1,null,null],["nvidia-geforce-rtx-2080-ti","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,51968,false,129.6,null,null],["nvidia-geforce-rtx-2080-ti","webworld-14b","cuda","fits","IQ2_M",8192,7.52,10240,false,97.4,null,null],["nvidia-geforce-rtx-2080-ti","webworld-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-2080-ti","webworld-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-2080-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,320.9,null,null],["nvidia-geforce-rtx-2080-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,320.9,null,null],["nvidia-geforce-rtx-2080-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,139.5,null,null],["nvidia-geforce-rtx-2080-ti","zwz-2b","cuda","fits","F16",8192,5.62,27904,false,140.6,null,null],["nvidia-geforce-rtx-2080-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,22528,false,136.6,null,null],["nvidia-geforce-rtx-2080-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,15104,false,98.2,null,null],["nvidia-geforce-rtx-2080-ti","zwz-8b","cuda","fits","Q5_K_M",8192,7.82,8448,false,93,null,null],["nvidia-geforce-rtx-3050-8gb","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,69.2,null,null],["nvidia-geforce-rtx-3050-8gb","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,69.2,null,null],["nvidia-geforce-rtx-3050-8gb","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,85.6,null,null],["nvidia-geforce-rtx-3050-8gb","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,85.6,null,null],["nvidia-geforce-rtx-3050-8gb","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,69.8,null,null],["nvidia-geforce-rtx-3050-8gb","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,64.5,null,null],["nvidia-geforce-rtx-3050-8gb","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,62.8,null,null],["nvidia-geforce-rtx-3050-8gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,72.9,null,null],["nvidia-geforce-rtx-3050-8gb","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,78,null,null],["nvidia-geforce-rtx-3050-8gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,71.6,null,null],["nvidia-geforce-rtx-3050-8gb","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,74.6,null,null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,67.9,null,null],["nvidia-geforce-rtx-3050-8gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,364.4,null,null],["nvidia-geforce-rtx-3050-8gb","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,71.3,null,null],["nvidia-geforce-rtx-3050-8gb","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,75,null,null],["nvidia-geforce-rtx-3050-8gb","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,393.4,null,null],["nvidia-geforce-rtx-3050-8gb","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,109.5,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,80.8,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,114.3,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,86.4,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,70.8,null,null],["nvidia-geforce-rtx-3050-8gb","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,70.5,null,null],["nvidia-geforce-rtx-3050-8gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,93.1,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,238.4,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,74.9,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,313.3,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,64.7,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,64.7,null,null],["nvidia-geforce-rtx-3050-8gb","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,64.7,null,null],["nvidia-geforce-rtx-3050-8gb","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,64.7,null,null],["nvidia-geforce-rtx-3050-8gb","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,68,null,null],["nvidia-geforce-rtx-3050-8gb","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,95.3,null,null],["nvidia-geforce-rtx-3050-8gb","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,311.4,null,null],["nvidia-geforce-rtx-3050-8gb","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,75.5,null,null],["nvidia-geforce-rtx-3050-8gb","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,118.9,null,null],["nvidia-geforce-rtx-3050-8gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,66.8,null,null],["nvidia-geforce-rtx-3050-8gb","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,66.8,null,null],["nvidia-geforce-rtx-3050-8gb","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,78.2,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,78.2,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,78.2,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,74.6,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,95.4,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,399.9,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,276.6,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,571.9,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,91.7,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,74.6,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,276.6,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,276.6,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,78.2,null,null],["nvidia-geforce-rtx-3050-8gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,81.7,null,null],["nvidia-geforce-rtx-3050-8gb","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,80.8,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,67.1,null,null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,139.5,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,139.5,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,139.5,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,242.6,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,242.6,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,242.6,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,81.7,null,null],["nvidia-geforce-rtx-3050-8gb","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,101.9,null,null],["nvidia-geforce-rtx-3050-8gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,67.1,null,null],["nvidia-geforce-rtx-3050-8gb","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,67.1,null,null],["nvidia-geforce-rtx-3050-8gb","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,63.7,null,null],["nvidia-geforce-rtx-3050-8gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,80.8,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-3050-8gb","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,75.2,null,null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,70.4,null,null],["nvidia-geforce-rtx-3050-8gb","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,62.5,null,null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,67.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,67.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,67.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,67.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,105.1,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,139.4,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,311.4,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,106.6,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,136.1,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,74.7,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,75.5,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-3050-8gb","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-3050-8gb","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,62.2,null,null],["nvidia-geforce-rtx-3050-8gb","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,71.6,null,null],["nvidia-geforce-rtx-3050-8gb","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,71.6,null,null],["nvidia-geforce-rtx-3050-8gb","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3050-8gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,89.3,null,null],["nvidia-geforce-rtx-3050-8gb","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,89.3,null,null],["nvidia-geforce-rtx-3050-8gb","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,89.3,null,null],["nvidia-geforce-rtx-3050-8gb","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,89.3,null,null],["nvidia-geforce-rtx-3050-8gb","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,80.8,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3050-8gb","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,323.6,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,334.9,null,null],["nvidia-geforce-rtx-3050-8gb","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,312.2,null,null],["nvidia-geforce-rtx-3050-8gb","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-3050-8gb","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3050-8gb","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,75,null,null],["nvidia-geforce-rtx-3050-8gb","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3050-8gb","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3050-8gb","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,116.7,null,null],["nvidia-geforce-rtx-3050-8gb","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,116.7,null,null],["nvidia-geforce-rtx-3050-8gb","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,67.3,null,null],["nvidia-geforce-rtx-3050-8gb","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,80.9,null,null],["nvidia-geforce-rtx-3050-8gb","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,62.6,null,null],["nvidia-geforce-rtx-3050-8gb","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,67,null,null],["nvidia-geforce-rtx-3050-8gb","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,64.2,null,null],["nvidia-geforce-rtx-3060-ti","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-3060-ti","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-3060-ti","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-3060-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-3060-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-3060-ti","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,129,null,null],["nvidia-geforce-rtx-3060-ti","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,125.7,null,null],["nvidia-geforce-rtx-3060-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,145.8,null,null],["nvidia-geforce-rtx-3060-ti","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,156,null,null],["nvidia-geforce-rtx-3060-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,143.2,null,null],["nvidia-geforce-rtx-3060-ti","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-3060-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3060-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-3060-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,142.6,null,null],["nvidia-geforce-rtx-3060-ti","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-3060-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-3060-ti","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-3060-ti","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3060-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-3060-ti","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,172.7,null,null],["nvidia-geforce-rtx-3060-ti","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,141.7,null,null],["nvidia-geforce-rtx-3060-ti","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,140.9,null,null],["nvidia-geforce-rtx-3060-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,186.3,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,149.7,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3060-ti","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3060-ti","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3060-ti","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,136.1,null,null],["nvidia-geforce-rtx-3060-ti","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,190.5,null,null],["nvidia-geforce-rtx-3060-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-3060-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-3060-ti","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,237.9,null,null],["nvidia-geforce-rtx-3060-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-3060-ti","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-3060-ti","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,149.3,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,190.8,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3060-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,163.5,null,null],["nvidia-geforce-rtx-3060-ti","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,125.3,null,null],["nvidia-geforce-rtx-3060-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,134.1,null,null],["nvidia-geforce-rtx-3060-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3060-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3060-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3060-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3060-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3060-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3060-ti","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,163.3,null,null],["nvidia-geforce-rtx-3060-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,203.8,null,null],["nvidia-geforce-rtx-3060-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-3060-ti","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-3060-ti","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,127.4,null,null],["nvidia-geforce-rtx-3060-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-3060-ti","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,150.5,null,null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,140.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,125.1,null,null],["nvidia-geforce-rtx-3060-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,210.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,278.9,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,213.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,272.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-3060-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,149.4,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-3060-ti","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-3060-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,124.3,null,null],["nvidia-geforce-rtx-3060-ti","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-3060-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-3060-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3060-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3060-ti","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3060-ti","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3060-ti","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3060-ti","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3060-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3060-ti","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,647.1,null,null],["nvidia-geforce-rtx-3060-ti","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,669.8,null,null],["nvidia-geforce-rtx-3060-ti","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,624.3,null,null],["nvidia-geforce-rtx-3060-ti","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-3060-ti","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3060-ti","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-3060-ti","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3060-ti","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3060-ti","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-3060-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-3060-ti","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,134.7,null,null],["nvidia-geforce-rtx-3060-ti","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3060-ti","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3060-ti","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3060-ti","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-3070","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-3070","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-3070","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,138.4,null,null],["nvidia-geforce-rtx-3070","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-3070","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-3070","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-3070","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-3070","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,129,null,null],["nvidia-geforce-rtx-3070","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-3070","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,125.7,null,null],["nvidia-geforce-rtx-3070","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3070","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-3070","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,145.8,null,null],["nvidia-geforce-rtx-3070","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,156,null,null],["nvidia-geforce-rtx-3070","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3070","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-3070","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,143.2,null,null],["nvidia-geforce-rtx-3070","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-3070","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3070","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3070","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3070","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3070","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3070","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3070","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3070","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-3070","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-3070","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-3070","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-3070","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-3070","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-3070","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,142.6,null,null],["nvidia-geforce-rtx-3070","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-3070","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-3070","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-3070","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-3070","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3070","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-3070","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3070","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3070","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-3070","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-3070","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-3070","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-3070","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-3070","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-3070","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-3070","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,172.7,null,null],["nvidia-geforce-rtx-3070","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,141.7,null,null],["nvidia-geforce-rtx-3070","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,140.9,null,null],["nvidia-geforce-rtx-3070","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-3070","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3070","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-3070","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-3070","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3070","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,186.3,null,null],["nvidia-geforce-rtx-3070","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-3070","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,149.7,null,null],["nvidia-geforce-rtx-3070","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-3070","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3070","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3070","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3070","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3070","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,129.4,null,null],["nvidia-geforce-rtx-3070","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,136.1,null,null],["nvidia-geforce-rtx-3070","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,190.5,null,null],["nvidia-geforce-rtx-3070","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-3070","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3070","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-3070","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3070","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-3070","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-3070","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3070","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,237.9,null,null],["nvidia-geforce-rtx-3070","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-3070","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3070","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3070","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-3070","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3070","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-3070","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,133.5,null,null],["nvidia-geforce-rtx-3070","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-3070","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3070","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3070","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3070","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3070","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-3070","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-3070","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-3070","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3070","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3070","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3070","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3070","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-3070","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,149.3,null,null],["nvidia-geforce-rtx-3070","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,190.8,null,null],["nvidia-geforce-rtx-3070","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-3070","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-3070","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3070","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-3070","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-3070","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,183.5,null,null],["nvidia-geforce-rtx-3070","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-3070","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3070","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-3070","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-3070","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,156.4,null,null],["nvidia-geforce-rtx-3070","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3070","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-3070","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-3070","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,163.5,null,null],["nvidia-geforce-rtx-3070","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,125.3,null,null],["nvidia-geforce-rtx-3070","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3070","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3070","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3070","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,134.1,null,null],["nvidia-geforce-rtx-3070","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3070","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3070","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3070","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,279,null,null],["nvidia-geforce-rtx-3070","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-3070","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3070","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3070","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,485.1,null,null],["nvidia-geforce-rtx-3070","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,163.3,null,null],["nvidia-geforce-rtx-3070","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,203.8,null,null],["nvidia-geforce-rtx-3070","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3070","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3070","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-3070","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,134.2,null,null],["nvidia-geforce-rtx-3070","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3070","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3070","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,127.4,null,null],["nvidia-geforce-rtx-3070","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3070","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-3070","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3070","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-3070","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3070","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3070","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-3070","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-3070","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-3070","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,150.5,null,null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3070","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-3070","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-3070","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-3070","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,140.7,null,null],["nvidia-geforce-rtx-3070","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,125.1,null,null],["nvidia-geforce-rtx-3070","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3070","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3070","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3070","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,135.7,null,null],["nvidia-geforce-rtx-3070","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,210.2,null,null],["nvidia-geforce-rtx-3070","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-3070","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-3070","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-3070","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,278.9,null,null],["nvidia-geforce-rtx-3070","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,622.7,null,null],["nvidia-geforce-rtx-3070","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-3070","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,213.2,null,null],["nvidia-geforce-rtx-3070","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,272.2,null,null],["nvidia-geforce-rtx-3070","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-3070","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-3070","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,149.4,null,null],["nvidia-geforce-rtx-3070","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,151,null,null],["nvidia-geforce-rtx-3070","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-3070","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-3070","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-3070","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3070","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3070","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3070","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-3070","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,124.3,null,null],["nvidia-geforce-rtx-3070","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-3070","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-3070","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,143.3,null,null],["nvidia-geforce-rtx-3070","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-3070","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3070","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3070","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3070","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,178.5,null,null],["nvidia-geforce-rtx-3070","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3070","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3070","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,161.6,null,null],["nvidia-geforce-rtx-3070","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-3070","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-3070","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-3070","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-3070","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,647.1,null,null],["nvidia-geforce-rtx-3070","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,669.8,null,null],["nvidia-geforce-rtx-3070","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,624.3,null,null],["nvidia-geforce-rtx-3070","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-3070","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-3070","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,150,null,null],["nvidia-geforce-rtx-3070","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-3070","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,233.4,null,null],["nvidia-geforce-rtx-3070","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,134.7,null,null],["nvidia-geforce-rtx-3070","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,161.8,null,null],["nvidia-geforce-rtx-3070","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,125.2,null,null],["nvidia-geforce-rtx-3070","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,134,null,null],["nvidia-geforce-rtx-3070","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,128.4,null,null],["nvidia-geforce-rtx-3070-ti","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,187.9,null,null],["nvidia-geforce-rtx-3070-ti","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,187.9,null,null],["nvidia-geforce-rtx-3070-ti","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,232.3,null,null],["nvidia-geforce-rtx-3070-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,232.3,null,null],["nvidia-geforce-rtx-3070-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,189.4,null,null],["nvidia-geforce-rtx-3070-ti","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,175.1,null,null],["nvidia-geforce-rtx-3070-ti","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,170.5,null,null],["nvidia-geforce-rtx-3070-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,197.9,null,null],["nvidia-geforce-rtx-3070-ti","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,211.7,null,null],["nvidia-geforce-rtx-3070-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,194.3,null,null],["nvidia-geforce-rtx-3070-ti","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,202.6,null,null],["nvidia-geforce-rtx-3070-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,184.2,null,null],["nvidia-geforce-rtx-3070-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,989.1,null,null],["nvidia-geforce-rtx-3070-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,193.5,null,null],["nvidia-geforce-rtx-3070-ti","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,203.5,null,null],["nvidia-geforce-rtx-3070-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1067.9,null,null],["nvidia-geforce-rtx-3070-ti","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,297.3,null,null],["nvidia-geforce-rtx-3070-ti","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,219.3,null,null],["nvidia-geforce-rtx-3070-ti","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,310.3,null,null],["nvidia-geforce-rtx-3070-ti","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,234.4,null,null],["nvidia-geforce-rtx-3070-ti","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,192.3,null,null],["nvidia-geforce-rtx-3070-ti","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,191.3,null,null],["nvidia-geforce-rtx-3070-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,252.8,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,647,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,203.2,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,850.5,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,175.6,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,175.6,null,null],["nvidia-geforce-rtx-3070-ti","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,175.6,null,null],["nvidia-geforce-rtx-3070-ti","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,175.6,null,null],["nvidia-geforce-rtx-3070-ti","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,184.6,null,null],["nvidia-geforce-rtx-3070-ti","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,258.6,null,null],["nvidia-geforce-rtx-3070-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,845.1,null,null],["nvidia-geforce-rtx-3070-ti","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,205,null,null],["nvidia-geforce-rtx-3070-ti","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,322.8,null,null],["nvidia-geforce-rtx-3070-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,181.2,null,null],["nvidia-geforce-rtx-3070-ti","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,181.2,null,null],["nvidia-geforce-rtx-3070-ti","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,212.2,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,212.2,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,212.2,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,202.6,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,259,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1085.4,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,750.8,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1552.4,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,249,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,202.6,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,750.8,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,750.8,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,212.2,null,null],["nvidia-geforce-rtx-3070-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,221.9,null,null],["nvidia-geforce-rtx-3070-ti","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,170,null,null],["nvidia-geforce-rtx-3070-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,219.3,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,182,null,null],["nvidia-geforce-rtx-3070-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,378.6,null,null],["nvidia-geforce-rtx-3070-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,378.6,null,null],["nvidia-geforce-rtx-3070-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,378.6,null,null],["nvidia-geforce-rtx-3070-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,658.4,null,null],["nvidia-geforce-rtx-3070-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,658.4,null,null],["nvidia-geforce-rtx-3070-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,658.4,null,null],["nvidia-geforce-rtx-3070-ti","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,221.7,null,null],["nvidia-geforce-rtx-3070-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,276.6,null,null],["nvidia-geforce-rtx-3070-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,182.1,null,null],["nvidia-geforce-rtx-3070-ti","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,182.1,null,null],["nvidia-geforce-rtx-3070-ti","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,172.9,null,null],["nvidia-geforce-rtx-3070-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,219.3,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-3070-ti","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,204.2,null,null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,191,null,null],["nvidia-geforce-rtx-3070-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,169.8,null,null],["nvidia-geforce-rtx-3070-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,184.2,null,null],["nvidia-geforce-rtx-3070-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,184.2,null,null],["nvidia-geforce-rtx-3070-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,184.2,null,null],["nvidia-geforce-rtx-3070-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,184.2,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,285.2,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,378.5,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,845.1,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,289.3,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,369.4,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-3070-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,202.8,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,205,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-3070-ti","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-3070-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,168.7,null,null],["nvidia-geforce-rtx-3070-ti","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,194.4,null,null],["nvidia-geforce-rtx-3070-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,194.4,null,null],["nvidia-geforce-rtx-3070-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3070-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,242.3,null,null],["nvidia-geforce-rtx-3070-ti","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,242.3,null,null],["nvidia-geforce-rtx-3070-ti","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,242.3,null,null],["nvidia-geforce-rtx-3070-ti","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,242.3,null,null],["nvidia-geforce-rtx-3070-ti","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,219.3,null,null],["nvidia-geforce-rtx-3070-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3070-ti","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,878.2,null,null],["nvidia-geforce-rtx-3070-ti","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,909,null,null],["nvidia-geforce-rtx-3070-ti","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,847.3,null,null],["nvidia-geforce-rtx-3070-ti","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-3070-ti","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3070-ti","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,203.5,null,null],["nvidia-geforce-rtx-3070-ti","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-3070-ti","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-3070-ti","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,316.7,null,null],["nvidia-geforce-rtx-3070-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,316.7,null,null],["nvidia-geforce-rtx-3070-ti","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,182.8,null,null],["nvidia-geforce-rtx-3070-ti","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,219.7,null,null],["nvidia-geforce-rtx-3070-ti","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,169.9,null,null],["nvidia-geforce-rtx-3070-ti","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,181.8,null,null],["nvidia-geforce-rtx-3070-ti","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,174.3,null,null],["nvidia-geforce-rtx-3080-10gb","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","aescode-8b","cuda","fits","IQ4_XS",8192,6.77,8704,false,136.7,null,null],["nvidia-geforce-rtx-3080-10gb","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,15872,false,168.6,null,null],["nvidia-geforce-rtx-3080-10gb","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,262144,false,234.8,null,null],["nvidia-geforce-rtx-3080-10gb","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,262144,false,234.8,null,null],["nvidia-geforce-rtx-3080-10gb","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,290.4,null,null],["nvidia-geforce-rtx-3080-10gb","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,290.4,null,null],["nvidia-geforce-rtx-3080-10gb","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,236.7,null,null],["nvidia-geforce-rtx-3080-10gb","apriel-1-6-15b-thinker","cuda","tight","Q5_K_M",8192,12.47,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","aprielguard","cuda","fits","Q4_K_M",8192,6.46,12288,false,143.9,null,null],["nvidia-geforce-rtx-3080-10gb","armorocr","cuda","tight","Q8_0",8192,10.39,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","astabrief-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","autoglm-phone-9b","cuda","fits","IQ4_XS",8192,6.53,16384,false,143.1,null,null],["nvidia-geforce-rtx-3080-10gb","autoglm-phone-9b-multilingual","cuda","fits","Q4_0",8192,6.67,13056,false,139.3,null,null],["nvidia-geforce-rtx-3080-10gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","bielik-11b-v3-0-instruct","cuda","tight","Q6_K",8192,11.8,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,247.3,null,null],["nvidia-geforce-rtx-3080-10gb","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","contextpilot-14b","cuda","tight","Q4_K_M",8192,11.31,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","contextpilot-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,20736,false,148.5,null,null],["nvidia-geforce-rtx-3080-10gb","cosmos-reason2-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","cosmos-reason2-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","d1-3b","cuda","fits","BF16",8192,6.7,17664,false,137.5,null,null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-0528-qwen3-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-distill-llama-8b","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-distill-qwen-14b","cuda","tight","Q4_K_M",8192,11.28,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","deepseek-r1-distill-qwen-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","devstral-small-2-24b-instruct-2512","cuda","tight","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","eurollm-22b-2512","cuda","tight","IQ3_XXS",8192,11.5,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","eurollm-22b-instruct-2512","cuda","tight","IQ3_XXS",8192,11.5,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","eurollm-9b-instruct-2512","cuda","fits","Q2_K",8192,6.01,13056,false,157.4,null,null],["nvidia-geforce-rtx-3080-10gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1236.4,null,null],["nvidia-geforce-rtx-3080-10gb","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","fara-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","fara1-5-27b","cuda","tight","IQ2_M",8192,12.54,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,22528,false,160,null,null],["nvidia-geforce-rtx-3080-10gb","fara1-5-9b","cuda","fits","Q4_0",8192,6.79,10496,false,147.1,null,null],["nvidia-geforce-rtx-3080-10gb","frogboss-32b-2510","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","frogmini-14b-2510","cuda","fits","IQ2_XXS",8192,6.6,9728,false,141.3,null,null],["nvidia-geforce-rtx-3080-10gb","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,22528,false,160,null,null],["nvidia-geforce-rtx-3080-10gb","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1334.9,null,null],["nvidia-geforce-rtx-3080-10gb","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","gemma-2-9b-it","cuda","tight","Q6_K",8192,11.96,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-3-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,371.6,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,34304,false,172.2,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","gemma-4-12b-it","cuda","tight","Q6_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-26b-a4b-it","cuda","tight","IQ2_M",8192,13.12,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,387.9,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,100096,false,163.3,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,17408,false,146.8,null,null],["nvidia-geforce-rtx-3080-10gb","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,8704,false,142.4,null,null],["nvidia-geforce-rtx-3080-10gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"7",null],["nvidia-geforce-rtx-3080-10gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","glm-4-6v-flash","cuda","fits","Q4_0",8192,6.67,13056,false,139.3,null,null],["nvidia-geforce-rtx-3080-10gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","gpt-oss-20b","cuda","tight","Q2_K",8192,12.56,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","granite-3-3-8b-instruct","cuda","fits","Q3_K_M",8192,6.51,10240,false,142.4,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-0-1b","cuda","fits","BF16",8192,5.14,29184,false,193.1,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,808.7,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,254,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1063.1,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","granite-4-1-3b","cuda","fits","Q8_0",8192,5.48,25088,false,177.3,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-1-8b","cuda","fits","Q3_K_M",8192,6.68,9216,false,138,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","granite-4-2-3b","cuda","fits","Q8_0",8192,5.48,25088,false,177.3,null,null],["nvidia-geforce-rtx-3080-10gb","granite-4-2-8b","cuda","fits","Q3_K_M",8192,6.68,9216,false,138,null,null],["nvidia-geforce-rtx-3080-10gb","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q3_K_M",8192,6.51,10240,false,142.4,null,null],["nvidia-geforce-rtx-3080-10gb","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,34816,false,219.5,null,null],["nvidia-geforce-rtx-3080-10gb","granite-guardian-4-1-8b","cuda","fits","Q3_K_M",8192,6.68,9216,false,138,null,null],["nvidia-geforce-rtx-3080-10gb","granite-vision-4-1-4b","cuda","fits","Q8_0",8192,5.48,25088,false,177.3,null,null],["nvidia-geforce-rtx-3080-10gb","harc-llama-3-1-8b-instruct","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","harc-qwen2-5-7b-instruct","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,36352,false,323.2,null,null],["nvidia-geforce-rtx-3080-10gb","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1056.4,null,null],["nvidia-geforce-rtx-3080-10gb","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,22784,false,160.3,null,null],["nvidia-geforce-rtx-3080-10gb","holo-3-1-9b","cuda","fits","IQ4_XS",8192,6.57,16896,false,153.7,null,null],["nvidia-geforce-rtx-3080-10gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","holo2-4b","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","holo2-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","holo4-27b","cuda","tight","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","holo4-35b-a3b","cuda","tight","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,403.5,null,null],["nvidia-geforce-rtx-3080-10gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8",null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","ising-calibration-1-35b-a3b","cuda","tight","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","januscoder-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","januscoder-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","januscoderv-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,23296,false,206.3,null,null],["nvidia-geforce-rtx-3080-10gb","kanana-2-3b-instruct","cuda","fits","Q8_0",8192,5.65,17408,false,170.6,null,null],["nvidia-geforce-rtx-3080-10gb","kat-coder-v2-5-dev","cuda","tight","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ2_XXS",8192,10.67,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","laguna-xs-2-1","cuda","tight","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,31488,false,144.1,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,31488,false,144.1,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,31488,false,144.1,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,17664,false,137.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,323.7,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1356.8,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,938.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-8b-a1b","cuda","fits","Q4_K_M",8192,6.43,39936,false,650.6,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1940.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,311.3,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,17664,false,137.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,938.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,938.5,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-8b-a1b","cuda","fits","Q4_K_M",8192,6.32,47360,false,714.9,null,null],["nvidia-geforce-rtx-3080-10gb","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,31488,false,144.1,null,null],["nvidia-geforce-rtx-3080-10gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","llama-3-1-8b-instruct","cuda","fits","Q4_K_M",8192,6.86,8192,false,133.5,null,null],["nvidia-geforce-rtx-3080-10gb","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,93184,false,277.4,null,null],["nvidia-geforce-rtx-3080-10gb","llama-3-2-3b-instruct","cuda","fits","Q8_0",8192,5.55,19712,false,174.6,null,null],["nvidia-geforce-rtx-3080-10gb","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","mathform-8b","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,34304,false,172.2,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q6_K",8192,12.08,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-12b-a2-5b-base","cuda","fits","IQ3_XXS",8192,6.81,12288,false,646.4,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-12b-a2-5b-instruct","cuda","fits","Q2_K",8192,6.58,26368,false,585.3,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-12b-a2-5b-instruct-sft","cuda","fits","IQ3_XXS",8192,6.81,12288,false,646.4,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-12b-a2-5b-thinking","cuda","fits","Q2_K",8192,6.58,26368,false,585.3,null,null],["nvidia-geforce-rtx-3080-10gb","mellum2-12b-a2-5b-thinking-sft","cuda","fits","IQ3_XXS",8192,6.81,12288,false,646.4,null,null],["nvidia-geforce-rtx-3080-10gb","mimo-embodied-7b","cuda","fits","Q4_K_M",8192,6.75,8960,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-6-distill-qwen-9b","cuda","fits","Q4_0",8192,6.79,10496,false,147.1,null,null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","minicpm-o-4-5","cuda","fits","Q4_0",8192,6.84,8448,false,135.1,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,473.2,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,473.2,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,473.2,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,822.9,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,822.9,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,822.9,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm5-2b","cuda","fits","BF16",8192,6.04,27136,false,156.7,null,null],["nvidia-geforce-rtx-3080-10gb","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,86016,false,345.8,null,null],["nvidia-geforce-rtx-3080-10gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8",null],["nvidia-geforce-rtx-3080-10gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ministral-3-3b-instruct-2512","cuda","fits","Q8_0",8192,5.71,18944,false,168.3,null,null],["nvidia-geforce-rtx-3080-10gb","ministral-3-3b-reasoning-2512","cuda","fits","Q8_0",8192,5.71,18944,false,168.3,null,null],["nvidia-geforce-rtx-3080-10gb","ministral-3-8b-instruct-2512","cuda","tight","Q8_0",8192,10.68,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ministral-3-8b-reasoning-2512","cuda","tight","Q8_0",8192,10.68,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","mistral-7b-instruct-v0-2","cuda","fits","Q4_K_M",8192,6.54,10496,false,141.6,null,null],["nvidia-geforce-rtx-3080-10gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","mistral-nemo-instruct-2407","cuda","fits","IQ2_M",8192,6.65,9472,false,138.7,null,null],["nvidia-geforce-rtx-3080-10gb","mistral-small-3-2-24b-instruct-2506","cuda","tight","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","muse-glimmer-30b","cuda","tight","IQ3_XXS",8192,12.61,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,76032,false,218.8,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"5",null],["nvidia-geforce-rtx-3080-10gb","nemotron-cascade-14b-thinking","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","nemotron-cascade-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-cascade-8b-thinking","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-orchestrator-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-terminal-14b","cuda","fits","IQ2_XXS",8192,6.6,9728,false,141.3,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-terminal-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","nemotron-terminal-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","north-mini-code-1-0","cuda","tight","IQ2_M",8192,12.7,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","nouscoder-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q8_0",8192,5.46,86528,false,193.7,null,null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","nvidia-nemotron-nano-9b-v2","cuda","fits","IQ4_XS",8192,6.81,11520,false,150.1,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1-7b-rl-zero-math","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-1125-32b","cuda","tight","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","olmo-3-32b-think-dpo","cuda","tight","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-32b-think-sft","cuda","tight","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-instruct","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-think","cuda","tight","Q8_0",8192,12.68,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","olmocr-2-7b-1025","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","phi-3-5-mini-instruct","cuda","fits","Q4_K_M",8192,6.73,8448,false,136.7,null,null],["nvidia-geforce-rtx-3080-10gb","phi-4","cuda","tight","Q4_K_M",8192,11.35,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,11264,false,147.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"7",null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-14b-instruct","cuda","tight","Q4_K_M",8192,11.28,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,212.2,null,null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-7b-instruct","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-coder-7b-instruct","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-vl-7b-instruct","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-0-6b","cuda","fits","BF16",8192,3.41,38400,false,356.5,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-1-7b","cuda","fits","BF16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-14b","cuda","tight","Q5_K_M",8192,12.41,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"4",null],["nvidia-geforce-rtx-3080-10gb","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"5",null],["nvidia-geforce-rtx-3080-10gb","qwen3-4b","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,473.1,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1056.4,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8",null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-2b","cuda","fits","BF16",8192,5.38,114176,false,196.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,461.7,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-35b-a3b-base","cuda","tight","IQ2_XXS",8192,10.92,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,22784,false,160.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,22784,false,160.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-9b","cuda","fits","Q4_0",8192,6.69,13568,false,150.1,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-5-9b-base","cuda","fits","IQ4_XS",8192,6.57,16896,false,153.7,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-6-35b-a3b","cuda","tight","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","qwen3-8-27b","cuda","tight","Q2_K",8192,12.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-8-3-6-27b-blend","cuda","tight","Q2_K",8192,12.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-8b","cuda","tight","Q8_0",8192,10.39,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"5",null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-reap-25b-a3b","cuda","tight","IQ3_XXS",8192,11.77,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","qwen3-nemotron-14b-brrm","cuda","fits","IQ2_XXS",8192,6.6,9728,false,141.3,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","qwen3-nemotron-8b-brrm","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-8b-instruct","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","qwen3-vl-8b-thinking","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"5",null],["nvidia-geforce-rtx-3080-10gb","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,158.7,null,null],["nvidia-geforce-rtx-3080-10gb","rlvr-8b-0926","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","rnj-1-instruct","cuda","fits","IQ4_XS",8192,6.83,8448,false,134.2,null,null],["nvidia-geforce-rtx-3080-10gb","sera-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","singguard-2b","cuda","fits","F16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","smollm3-3b","cuda","fits","Q8_0",8192,5.08,32256,false,196.3,null,null],["nvidia-geforce-rtx-3080-10gb","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,42240,false,243,null,null],["nvidia-geforce-rtx-3080-10gb","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"6",null],["nvidia-geforce-rtx-3080-10gb","spatial-ssrl-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,9216,false,138.6,null,null],["nvidia-geforce-rtx-3080-10gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"7",null],["nvidia-geforce-rtx-3080-10gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8",null],["nvidia-geforce-rtx-3080-10gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-10gb","step3-vl-10b-base","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","tiny-aya-earth","cuda","fits","Q8_0",8192,5.64,45312,false,193.1,null,null],["nvidia-geforce-rtx-3080-10gb","tiny-aya-fire","cuda","fits","Q8_0",8192,5.64,45312,false,193.1,null,null],["nvidia-geforce-rtx-3080-10gb","tiny-aya-global","cuda","fits","Q8_0",8192,5.64,45312,false,193.1,null,null],["nvidia-geforce-rtx-3080-10gb","tiny-aya-water","cuda","fits","Q8_0",8192,5.64,45312,false,193.1,null,null],["nvidia-geforce-rtx-3080-10gb","translategemma-12b-it","cuda","tight","Q6_K",8192,13.02,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,34304,false,172.2,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-10gb","trinity-mini","cuda","tight","IQ3_XXS",8192,12.12,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-mini-base","cuda","tight","IQ3_XXS",8192,11.76,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-mini-base-pre-anneal","cuda","tight","IQ3_XXS",4096,11.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,19200,false,843.9,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,902.7,null,null],["nvidia-geforce-rtx-3080-10gb","trinity-nano-preview","cuda","fits","Q6_K",8192,6.69,18176,false,831.1,null,null],["nvidia-geforce-rtx-3080-10gb","ui-mate-27b","cuda","tight","IQ2_M",8192,12.54,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ui-mate-9b","cuda","fits","Q4_0",8192,6.79,10496,false,147.1,null,null],["nvidia-geforce-rtx-3080-10gb","ui-mate-democua-27b","cuda","tight","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-3080-10gb","ui-venus-1-5-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-10gb","ui-venus-2-9b","cuda","fits","Q4_0",8192,6.79,10496,false,147.1,null,null],["nvidia-geforce-rtx-3080-10gb","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,22528,false,160,null,null],["nvidia-geforce-rtx-3080-10gb","webworld-14b","cuda","fits","IQ2_XXS",8192,6.6,9728,false,141.3,null,null],["nvidia-geforce-rtx-3080-10gb","webworld-32b","cuda","tight","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-geforce-rtx-3080-10gb","webworld-8b","cuda","fits","IQ4_XS",8192,6.68,9472,false,139.1,null,null],["nvidia-geforce-rtx-3080-10gb","x-reasoner-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,105472,false,395.9,null,null],["nvidia-geforce-rtx-3080-10gb","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,105472,false,395.9,null,null],["nvidia-geforce-rtx-3080-10gb","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,28416,false,172.2,null,null],["nvidia-geforce-rtx-3080-10gb","zwz-2b","cuda","fits","F16",8192,5.62,18944,false,173.5,null,null],["nvidia-geforce-rtx-3080-10gb","zwz-4b","cuda","fits","Q6_K",8192,5.74,15872,false,168.6,null,null],["nvidia-geforce-rtx-3080-10gb","zwz-7b","cuda","fits","Q5_K_M",8192,6.75,10240,false,137.3,null,null],["nvidia-geforce-rtx-3080-10gb","zwz-8b","cuda","fits","Q4_0",8192,6.85,8192,false,134.8,null,null],["nvidia-geforce-rtx-3080-ti","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","aescode-8b","cuda","fits","Q5_K_M",8192,8.2,12544,false,130,null,null],["nvidia-geforce-rtx-3080-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,29440,false,202.3,null,null],["nvidia-geforce-rtx-3080-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,150.2,null,null],["nvidia-geforce-rtx-3080-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,150.2,null,null],["nvidia-geforce-rtx-3080-ti","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,348.4,null,null],["nvidia-geforce-rtx-3080-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,348.4,null,null],["nvidia-geforce-rtx-3080-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,284,null,null],["nvidia-geforce-rtx-3080-ti","apriel-1-6-15b-thinker","cuda","fits","IQ3_XXS",8192,8.24,11264,false,128.5,null,null],["nvidia-geforce-rtx-3080-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,18176,false,135.6,null,null],["nvidia-geforce-rtx-3080-ti","armorocr","cuda","fits","Q4_K_M",8192,7.09,20224,false,155.1,null,null],["nvidia-geforce-rtx-3080-ti","astabrief-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","autoglm-phone-9b","cuda","fits","Q5_K_M",8192,8.13,25600,false,131.2,null,null],["nvidia-geforce-rtx-3080-ti","autoglm-phone-9b-multilingual","cuda","fits","Q5_K_M",8192,8.13,25600,false,131.2,null,null],["nvidia-geforce-rtx-3080-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","bielik-11b-v3-0-instruct","cuda","tight","Q8_0",8192,14.42,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q6_K",8192,8.5,10240,false,123.8,null,null],["nvidia-geforce-rtx-3080-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,296.8,null,null],["nvidia-geforce-rtx-3080-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","contextpilot-14b","cuda","fits","IQ3_XXS",8192,8.43,10752,false,125.7,null,null],["nvidia-geforce-rtx-3080-ti","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,131072,false,178.2,null,null],["nvidia-geforce-rtx-3080-ti","cosmos-reason2-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,164.9,null,null],["nvidia-geforce-rtx-3080-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-distill-llama-8b","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-distill-qwen-14b","cuda","fits","Q2_K",8192,8.3,11008,false,128.1,null,null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","devstral-small-2-24b-instruct-2512","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","eurollm-22b-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","eurollm-22b-instruct-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","eurollm-9b-instruct-2512","cuda","fits","Q5_K_M",8192,8.69,9216,false,120.6,null,null],["nvidia-geforce-rtx-3080-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1483.7,null,null],["nvidia-geforce-rtx-3080-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","fara-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","fara1-5-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,81152,false,191.9,null,null],["nvidia-geforce-rtx-3080-ti","fara1-5-9b","cuda","fits","Q6_K",8192,8.7,13056,false,128,null,null],["nvidia-geforce-rtx-3080-ti","frogboss-32b-2510","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","frogmini-14b-2510","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,81152,false,191.9,null,null],["nvidia-geforce-rtx-3080-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1601.9,null,null],["nvidia-geforce-rtx-3080-ti","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","gemma-2-27b-it","cuda","tight","IQ3_XXS",8192,15.11,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","gemma-2-9b-it","cuda","fits","IQ3_XXS",8192,8.03,8192,false,154.5,null,null],["nvidia-geforce-rtx-3080-ti","gemma-3-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,161.9,null,null],["nvidia-geforce-rtx-3080-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,445.9,null,null],["nvidia-geforce-rtx-3080-ti","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,206.6,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-12b-it","cuda","fits","Q3_K_M",8192,8.73,16128,false,148.3,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-26b-a4b-it","cuda","tight","Q3_K_M",8192,15.39,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,465.5,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,195.9,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,128256,false,176.2,null,null],["nvidia-geforce-rtx-3080-ti","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,119296,false,170.9,null,null],["nvidia-geforce-rtx-3080-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","glm-4-6v-flash","cuda","fits","Q5_K_M",8192,8.13,25600,false,131.2,null,null],["nvidia-geforce-rtx-3080-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q4_0",8192,14.61,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","granite-3-3-8b-instruct","cuda","fits","Q5_K_M",8192,8.28,11776,false,127.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,53504,false,231.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,970.5,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,304.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1275.7,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-1-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-1-3b","cuda","fits","BF16",8192,8.61,11264,false,122,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,124.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-2-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-2-3b","cuda","fits","BF16",8192,8.61,11264,false,122,null,null],["nvidia-geforce-rtx-3080-ti","granite-4-2-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,124.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q5_K_M",8192,8.28,11776,false,127.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,59136,false,263.3,null,null],["nvidia-geforce-rtx-3080-ti","granite-guardian-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,124.8,null,null],["nvidia-geforce-rtx-3080-ti","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,11264,false,122,null,null],["nvidia-geforce-rtx-3080-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,387.9,null,null],["nvidia-geforce-rtx-3080-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1267.6,null,null],["nvidia-geforce-rtx-3080-ti","holo-3-1-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,81408,false,192.4,null,null],["nvidia-geforce-rtx-3080-ti","holo-3-1-9b","cuda","fits","Q6_K",8192,8.37,22784,false,134.5,null,null],["nvidia-geforce-rtx-3080-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","holo2-4b","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","holo2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","holo3-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","holo4-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","holo4-35b-a3b","cuda","tight","Q2_K",8192,14.96,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,484.2,null,null],["nvidia-geforce-rtx-3080-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","ising-calibration-1-35b-a3b","cuda","tight","IQ3_XXS",8192,15.07,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ising-calibration-1-5-31b-bf16","cuda","tight","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","januscoder-14b","cuda","fits","Q2_K",8192,8.02,13312,false,133.4,null,null],["nvidia-geforce-rtx-3080-ti","januscoder-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,247.6,null,null],["nvidia-geforce-rtx-3080-ti","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,10496,false,122.7,null,null],["nvidia-geforce-rtx-3080-ti","kat-coder-v2-5-dev","cuda","tight","Q2_K",8192,14.13,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"4",null],["nvidia-geforce-rtx-3080-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","kimi-linear-48b-a3b-base","cuda","tight","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ3_XXS",8192,14.77,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,172.9,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,172.9,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,172.9,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-24b-a2b","cuda","tight","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,128256,false,164.9,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,388.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1628.1,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-24b-a2b","cuda","tight","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,1126.3,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-8b-a1b","cuda","fits","Q6_K",8192,8.19,56576,false,612.6,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,2328.6,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,373.5,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,164.9,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,1126.3,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,1126.3,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-8b-a1b","cuda","fits","Q6_K",8192,8.09,63744,false,659.1,null,null],["nvidia-geforce-rtx-3080-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,172.9,null,null],["nvidia-geforce-rtx-3080-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,126.1,null,null],["nvidia-geforce-rtx-3080-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,332.8,null,null],["nvidia-geforce-rtx-3080-ti","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,11264,false,123.8,null,null],["nvidia-geforce-rtx-3080-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-3080-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","mathform-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,206.6,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q8_0",8192,14.03,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-12b-a2-5b-base","cuda","fits","Q4_0",8192,8.27,45824,false,615.3,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q4_0",8192,8.34,41728,false,588.7,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q4_0",8192,8.27,45824,false,615.3,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q4_0",8192,8.34,41728,false,588.7,null,null],["nvidia-geforce-rtx-3080-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q4_0",8192,8.27,45824,false,615.3,null,null],["nvidia-geforce-rtx-3080-ti","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,13056,false,131.2,null,null],["nvidia-geforce-rtx-3080-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","Q6_K",8192,8.8,10240,false,126.4,null,null],["nvidia-geforce-rtx-3080-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","minicpm-o-4-5","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,567.9,null,null],["nvidia-geforce-rtx-3080-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,567.9,null,null],["nvidia-geforce-rtx-3080-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,567.9,null,null],["nvidia-geforce-rtx-3080-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,987.5,null,null],["nvidia-geforce-rtx-3080-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,987.5,null,null],["nvidia-geforce-rtx-3080-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,987.5,null,null],["nvidia-geforce-rtx-3080-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,72448,false,188,null,null],["nvidia-geforce-rtx-3080-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,131328,false,414.9,null,null],["nvidia-geforce-rtx-3080-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,8192,false,118,null,null],["nvidia-geforce-rtx-3080-ti","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,8192,false,118,null,null],["nvidia-geforce-rtx-3080-ti","ministral-3-8b-instruct-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,133.7,null,null],["nvidia-geforce-rtx-3080-ti","ministral-3-8b-reasoning-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,133.7,null,null],["nvidia-geforce-rtx-3080-ti","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,14336,false,132,null,null],["nvidia-geforce-rtx-3080-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","mistral-nemo-instruct-2407","cuda","fits","IQ4_XS",8192,8.85,8192,false,118.1,null,null],["nvidia-geforce-rtx-3080-ti","mistral-small-3-2-24b-instruct-2506","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","muse-glimmer-30b","cuda","tight","Q3_K_M",8192,14.97,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,262.6,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-rtx-3080-ti","nemotron-cascade-14b-thinking","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","nemotron-cascade-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-cascade-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-orchestrator-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-terminal-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-terminal-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","north-mini-code-1-0","cuda","tight","IQ3_XXS",8192,15.09,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","nouscoder-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,15872,false,125.6,null,null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"7",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","Q5_K_M",8192,8.47,30208,false,135,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1-32b-instruct","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1-7b-rl-zero-math","cuda","fits","Q2_K",8192,8.17,9472,false,168.8,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-1125-32b","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-32b-think-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-32b-think-sft","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-instruct","cuda","fits","Q2_K",8192,8.17,9472,false,168.8,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-instruct-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-instruct-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-rl-zero-general","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-rl-zero-if","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-rl-zero-math","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-rl-zero-mix","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-think","cuda","fits","Q2_K",8192,8.17,9472,false,168.8,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-think-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmo-3-7b-think-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,168.7,null,null],["nvidia-geforce-rtx-3080-ti","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,9472,false,127.1,null,null],["nvidia-geforce-rtx-3080-ti","phi-4","cuda","fits","Q2_K",8192,8.25,11008,false,128.2,null,null],["nvidia-geforce-rtx-3080-ti","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,26624,false,177.1,null,null],["nvidia-geforce-rtx-3080-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","qwen2-5-14b-instruct","cuda","fits","Q2_K",8192,8.3,11008,false,128.1,null,null],["nvidia-geforce-rtx-3080-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,254.6,null,null],["nvidia-geforce-rtx-3080-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,427.8,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-14b","cuda","tight","Q6_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,567.7,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1267.6,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","qwen3-5-27b","cuda","tight","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,256512,false,235.9,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,554,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","qwen3-5-35b-a3b-base","cuda","tight","IQ3_XXS",8192,14.98,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,81408,false,192.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,81408,false,192.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-9b","cuda","fits","Q6_K",8192,8.47,19968,false,132.5,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-5-9b-base","cuda","fits","Q6_K",8192,8.37,22784,false,134.5,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","qwen3-6-35b-a3b","cuda","tight","Q2_K",8192,14.12,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","qwen3-8-27b","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-8-3-6-27b-blend","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-reap-25b-a3b","cuda","fits","IQ2_XXS",8192,8.11,15872,false,486.9,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-3080-ti","qwen3-nemotron-14b-brrm","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-8b-instruct","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","qwen3-vl-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"3",null],["nvidia-geforce-rtx-3080-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,190.4,null,null],["nvidia-geforce-rtx-3080-ti","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","rnj-1-instruct","cuda","fits","Q5_K_M",8192,8.15,13568,false,130.1,null,null],["nvidia-geforce-rtx-3080-ti","sera-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","singguard-2b","cuda","fits","F16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","smollm3-3b","cuda","fits","BF16",8192,7.9,21248,false,135,null,null],["nvidia-geforce-rtx-3080-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,291.7,null,null],["nvidia-geforce-rtx-3080-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,166.4,null,null],["nvidia-geforce-rtx-3080-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8",null],["nvidia-geforce-rtx-3080-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"5",null],["nvidia-geforce-rtx-3080-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"6",null],["nvidia-geforce-rtx-3080-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","tiny-aya-earth","cuda","fits","BF16",8192,8.72,10240,false,128.9,null,null],["nvidia-geforce-rtx-3080-ti","tiny-aya-fire","cuda","fits","BF16",8192,8.72,10240,false,128.9,null,null],["nvidia-geforce-rtx-3080-ti","tiny-aya-global","cuda","fits","BF16",8192,8.72,10240,false,128.9,null,null],["nvidia-geforce-rtx-3080-ti","tiny-aya-water","cuda","fits","BF16",8192,8.72,10240,false,128.9,null,null],["nvidia-geforce-rtx-3080-ti","translategemma-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,161.9,null,null],["nvidia-geforce-rtx-3080-ti","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,206.6,null,null],["nvidia-geforce-rtx-3080-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3080-ti","trinity-mini","cuda","fits","IQ2_XXS",8192,8.25,41216,false,663.2,null,null],["nvidia-geforce-rtx-3080-ti","trinity-mini-base","cuda","fits","IQ2_XXS",8192,8.69,16640,false,732.6,null,null],["nvidia-geforce-rtx-3080-ti","trinity-mini-base-pre-anneal","cuda","fits","IQ2_XXS",4096,8.41,4096,false,774.3,null,null],["nvidia-geforce-rtx-3080-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,1012.7,null,null],["nvidia-geforce-rtx-3080-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,1083.3,null,null],["nvidia-geforce-rtx-3080-ti","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,56320,false,831.2,null,null],["nvidia-geforce-rtx-3080-ti","ui-mate-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ui-mate-9b","cuda","fits","Q6_K",8192,8.7,13056,false,128,null,null],["nvidia-geforce-rtx-3080-ti","ui-mate-democua-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","ui-venus-2-9b","cuda","fits","Q6_K",8192,8.7,13056,false,128,null,null],["nvidia-geforce-rtx-3080-ti","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,81152,false,191.9,null,null],["nvidia-geforce-rtx-3080-ti","webworld-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,131.3,null,null],["nvidia-geforce-rtx-3080-ti","webworld-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-3080-ti","webworld-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3080-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,475,null,null],["nvidia-geforce-rtx-3080-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,475,null,null],["nvidia-geforce-rtx-3080-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,206.6,null,null],["nvidia-geforce-rtx-3080-ti","zwz-2b","cuda","fits","F16",8192,5.62,36608,false,208.2,null,null],["nvidia-geforce-rtx-3080-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,29440,false,202.3,null,null],["nvidia-geforce-rtx-3080-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,32256,false,145.4,null,null],["nvidia-geforce-rtx-3080-ti","zwz-8b","cuda","fits","Q6_K",8192,8.59,9984,false,123,null,null],["nvidia-geforce-rtx-3090","aescode-32b","cuda","fits","IQ4_XS",8192,20.78,10496,false,47.2,null,null],["nvidia-geforce-rtx-3090","aescode-8b","cuda","fits","BF16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,115200,false,207.6,null,null],["nvidia-geforce-rtx-3090","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,154.1,null,null],["nvidia-geforce-rtx-3090","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,154.1,null,null],["nvidia-geforce-rtx-3090","ai21-jamba2-mini","cuda","fits","IQ3_XXS",8192,21.21,20736,false,193.2,null,null],["nvidia-geforce-rtx-3090","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,357.6,null,null],["nvidia-geforce-rtx-3090","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,357.6,null,null],["nvidia-geforce-rtx-3090","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,291.5,null,null],["nvidia-geforce-rtx-3090","apriel-1-6-15b-thinker","cuda","fits","Q8_0",8192,17.19,29952,false,57.7,null,null],["nvidia-geforce-rtx-3090","aprielguard","cuda","fits","Q6_K",8192,7.87,131072,false,139.2,null,null],["nvidia-geforce-rtx-3090","armorocr","cuda","fits","Q8_0",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","astabrief-8b","cuda","fits","Q6_K",8192,8.59,40960,false,126.2,null,null],["nvidia-geforce-rtx-3090","autoglm-phone-9b","cuda","fits","F16",8192,18.87,65536,false,52.3,null,null],["nvidia-geforce-rtx-3090","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,115.8,null,null],["nvidia-geforce-rtx-3090","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3090","bielik-11b-v3-0-instruct","cuda","fits","Q8_0",8192,14.42,32768,false,69.8,null,null],["nvidia-geforce-rtx-3090","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,32768,false,102.3,null,null],["nvidia-geforce-rtx-3090","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,304.6,null,null],["nvidia-geforce-rtx-3090","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3090","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"4",null],["nvidia-geforce-rtx-3090","contextpilot-14b","cuda","fits","Q8_0",8192,17.21,34048,false,57.7,null,null],["nvidia-geforce-rtx-3090","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,40960,false,126.2,null,null],["nvidia-geforce-rtx-3090","contextpilot-e4b","cuda","fits","F16",8192,10.89,131072,false,99.1,null,null],["nvidia-geforce-rtx-3090","cosmos-reason2-32b","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,95744,false,126.2,null,null],["nvidia-geforce-rtx-3090","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,169.3,null,null],["nvidia-geforce-rtx-3090","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3090","deepseek-r1-0528-qwen3-8b","cuda","fits","BF16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"2",null],["nvidia-geforce-rtx-3090","deepseek-r1-distill-llama-8b","cuda","fits","BF16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","deepseek-r1-distill-qwen-14b","cuda","fits","Q8_0",8192,17.48,28416,false,56.8,null,null],["nvidia-geforce-rtx-3090","deepseek-r1-distill-qwen-32b","cuda","fits","Q3_K_M",8192,18.71,18688,false,52.8,null,null],["nvidia-geforce-rtx-3090","deepseek-r1-distill-qwen-7b","cuda","fits","F16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3090","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3090","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3090","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"3",null],["nvidia-geforce-rtx-3090","devstral-small-2-24b-instruct-2512","cuda","fits","Q6_K",8192,21.01,10752,false,46.5,null,null],["nvidia-geforce-rtx-3090","eurollm-22b-2512","cuda","fits","Q6_K",8192,20.63,11776,false,47.4,null,null],["nvidia-geforce-rtx-3090","eurollm-22b-instruct-2512","cuda","fits","Q6_K",8192,20.63,11776,false,47.4,null,null],["nvidia-geforce-rtx-3090","eurollm-9b-instruct-2512","cuda","fits","F16",8192,19.58,18944,false,50.1,null,null],["nvidia-geforce-rtx-3090","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1522.8,null,null],["nvidia-geforce-rtx-3090","exaone-4-5-33b","cuda","fits","IQ4_XS",8192,20.43,12032,false,50.2,null,null],["nvidia-geforce-rtx-3090","fara-7b","cuda","fits","BF16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","fara1-5-27b","cuda","fits","Q4_K_M",8192,19.13,42752,false,54,null,null],["nvidia-geforce-rtx-3090","fara1-5-4b","cuda","fits","BF16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","fara1-5-9b","cuda","fits","BF16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","frogboss-32b-2510","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","frogmini-14b-2510","cuda","fits","Q6_K",8192,13.89,40960,false,73,null,null],["nvidia-geforce-rtx-3090","frognano-4b-2609","cuda","fits","BF16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1644,null,null],["nvidia-geforce-rtx-3090","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","gemma-2-27b-it","cuda","fits","Q4_K_M",8192,20.89,8192,false,49.4,null,null],["nvidia-geforce-rtx-3090","gemma-2-9b-it","cuda","fits","Q8_0",8192,14.78,8192,false,73.2,null,null],["nvidia-geforce-rtx-3090","gemma-3-12b-it","cuda","fits","Q8_0",8192,15.82,92928,false,70,null,null],["nvidia-geforce-rtx-3090","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,457.7,null,null],["nvidia-geforce-rtx-3090","gemma-3-27b-it","cuda","fits","Q4_K_M",8192,20.35,21248,false,53,null,null],["nvidia-geforce-rtx-3090","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,116.3,null,null],["nvidia-geforce-rtx-3090","gemma-4-12b","cuda","fits","Q8_0",8192,15.57,262144,false,71.3,null,null],["nvidia-geforce-rtx-3090","gemma-4-12b-it","cuda","fits","Q8_0",8192,15.57,262144,false,71.3,null,null],["nvidia-geforce-rtx-3090","gemma-4-26b-a4b","cuda","fits","Q5_K_M",8192,21.38,10496,false,284.7,null,null],["nvidia-geforce-rtx-3090","gemma-4-26b-a4b-it","cuda","fits","Q4_K_M",8192,19.33,103680,false,291.4,null,null],["nvidia-geforce-rtx-3090","gemma-4-31b","cuda","fits","Q3_K_M",8192,20.88,14848,false,55.8,null,null],["nvidia-geforce-rtx-3090","gemma-4-31b-it","cuda","fits","Q3_K_M",8192,20.34,21248,false,57.7,null,null],["nvidia-geforce-rtx-3090","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,477.7,null,null],["nvidia-geforce-rtx-3090","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,201.1,null,null],["nvidia-geforce-rtx-3090","gemma-4-e4b","cuda","fits","F16",8192,11,131072,false,98,null,null],["nvidia-geforce-rtx-3090","gemma-4-e4b-it","cuda","fits","BF16",8192,11,131072,false,98,null,null],["nvidia-geforce-rtx-3090","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8",null],["nvidia-geforce-rtx-3090","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"3",null],["nvidia-geforce-rtx-3090","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"2",null],["nvidia-geforce-rtx-3090","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"6",null],["nvidia-geforce-rtx-3090","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"3",null],["nvidia-geforce-rtx-3090","glm-4-6v-flash","cuda","fits","BF16",8192,18.87,69120,false,52.3,null,null],["nvidia-geforce-rtx-3090","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8",null],["nvidia-geforce-rtx-3090","glm-4-7-flash","cuda","fits","Q4_K_M",8192,19.53,42752,false,328.9,null,null],["nvidia-geforce-rtx-3090","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q6_K",8192,20.11,32000,false,267.8,null,null],["nvidia-geforce-rtx-3090","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"5",null],["nvidia-geforce-rtx-3090","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"4",null],["nvidia-geforce-rtx-3090","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3090","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3090","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3090","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3090","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"5",null],["nvidia-geforce-rtx-3090","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"4",null],["nvidia-geforce-rtx-3090","gpt-oss-20b","cuda","fits","Q8_0",8192,12.9,131072,false,336.8,null,null],["nvidia-geforce-rtx-3090","granite-3-3-8b-instruct","cuda","fits","F16",8192,18.62,25344,false,52.9,null,null],["nvidia-geforce-rtx-3090","granite-4-0-1b","cuda","fits","BF16",8192,5.14,131072,false,237.9,null,null],["nvidia-geforce-rtx-3090","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,996,null,null],["nvidia-geforce-rtx-3090","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,312.8,null,null],["nvidia-geforce-rtx-3090","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1309.2,null,null],["nvidia-geforce-rtx-3090","granite-4-1-30b","cuda","fits","Q4_K_M",8192,20.53,11520,false,47.7,null,null],["nvidia-geforce-rtx-3090","granite-4-1-3b","cuda","fits","BF16",8192,8.61,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090","granite-4-1-8b","cuda","fits","BF16",8192,19.03,22784,false,51.7,null,null],["nvidia-geforce-rtx-3090","granite-4-2-30b","cuda","fits","Q4_K_M",8192,20.53,11520,false,47.7,null,null],["nvidia-geforce-rtx-3090","granite-4-2-3b","cuda","fits","BF16",8192,8.61,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090","granite-4-2-8b","cuda","fits","BF16",8192,19.03,22784,false,51.7,null,null],["nvidia-geforce-rtx-3090","granite-guardian-3-2-8b-factuality-detection","cuda","fits","F16",8192,18.62,25344,false,52.9,null,null],["nvidia-geforce-rtx-3090","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,131072,false,270.3,null,null],["nvidia-geforce-rtx-3090","granite-guardian-4-1-8b","cuda","fits","BF16",8192,19.03,22784,false,51.7,null,null],["nvidia-geforce-rtx-3090","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,108288,false,129.4,null,null],["nvidia-geforce-rtx-3090","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,149.3,null,null],["nvidia-geforce-rtx-3090","hermes-4-3-36b","cuda","fits","Q3_K_M",8192,20.37,12288,false,48.2,null,null],["nvidia-geforce-rtx-3090","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,398.1,null,null],["nvidia-geforce-rtx-3090","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1301,null,null],["nvidia-geforce-rtx-3090","holo-3-1-35b-a3b","cuda","fits","IQ4_XS",8192,20.23,62720,false,457.8,null,null],["nvidia-geforce-rtx-3090","holo-3-1-4b","cuda","fits","F16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","holo-3-1-9b","cuda","fits","F16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090","holo2-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","holo2-4b","cuda","fits","F16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","holo2-8b","cuda","fits","Q6_K",8192,8.59,95744,false,126.2,null,null],["nvidia-geforce-rtx-3090","holo3-35b-a3b","cuda","fits","IQ4_XS",8192,20.23,62720,false,457.8,null,null],["nvidia-geforce-rtx-3090","holo4-27b","cuda","fits","Q5_K_M",8192,20.64,19968,false,49.6,null,null],["nvidia-geforce-rtx-3090","holo4-35b-a3b","cuda","fits","Q4_0",8192,21.2,18944,false,429.6,null,null],["nvidia-geforce-rtx-3090","holotron4-30b-a3b","cuda","fits","Q4_0",8192,19.03,262144,true,450.5,null,null],["nvidia-geforce-rtx-3090","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,497,null,null],["nvidia-geforce-rtx-3090","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"5",null],["nvidia-geforce-rtx-3090","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"2",null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","F16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","F16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","F16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","F16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,40960,false,101.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,40960,false,101.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,40960,false,101.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,40960,false,101.2,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"7",null],["nvidia-geforce-rtx-3090","ising-calibration-1-35b-a3b","cuda","fits","Q4_0",8192,21.06,25344,false,459.8,null,null],["nvidia-geforce-rtx-3090","ising-calibration-1-5-31b-bf16","cuda","fits","IQ3_XXS",8192,18.62,42240,false,64.7,null,null],["nvidia-geforce-rtx-3090","januscoder-14b","cuda","fits","Q8_0",8192,17.21,32768,false,57.7,null,null],["nvidia-geforce-rtx-3090","januscoder-8b","cuda","fits","BF16",8192,17.35,32768,false,57.3,null,null],["nvidia-geforce-rtx-3090","januscoderv-7b","cuda","fits","BF16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"7",null],["nvidia-geforce-rtx-3090","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,254.1,null,null],["nvidia-geforce-rtx-3090","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,125.9,null,null],["nvidia-geforce-rtx-3090","kat-coder-v2-5-dev","cuda","fits","Q4_0",8192,21.2,18944,false,429.6,null,null],["nvidia-geforce-rtx-3090","kat-dev-72b-exp","cuda","tight","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-geforce-rtx-3090","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3090","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3090","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3090","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3090","kimi-linear-48b-a3b-base","cuda","fits","IQ3_XXS",8192,20.04,148992,false,659.7,null,null],["nvidia-geforce-rtx-3090","kimi-linear-48b-a3b-instruct","cuda","fits","IQ3_XXS",8192,20.69,83968,false,543.9,null,null],["nvidia-geforce-rtx-3090","kimi-linear-reap-35b-a3b-instruct","cuda","fits","Q4_0",8192,20.94,58112,false,479.1,null,null],["nvidia-geforce-rtx-3090","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090","laguna-xs-2-1","cuda","fits","Q4_0",8192,20.64,27136,false,405.2,null,null],["nvidia-geforce-rtx-3090","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,177.5,null,null],["nvidia-geforce-rtx-3090","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,177.5,null,null],["nvidia-geforce-rtx-3090","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,177.5,null,null],["nvidia-geforce-rtx-3090","lfm2-24b-a2b","cuda","fits","Q6_K",8192,20.64,44288,false,447.1,null,null],["nvidia-geforce-rtx-3090","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,169.3,null,null],["nvidia-geforce-rtx-3090","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,398.7,null,null],["nvidia-geforce-rtx-3090","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1671,null,null],["nvidia-geforce-rtx-3090","lfm2-5-24b-a2b","cuda","fits","Q6_K",8192,20.74,39680,false,425.8,null,null],["nvidia-geforce-rtx-3090","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,1155.9,null,null],["nvidia-geforce-rtx-3090","lfm2-5-8b-a1b","cuda","fits","BF16",8192,17.99,128000,false,269.3,null,null],["nvidia-geforce-rtx-3090","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,2389.8,null,null],["nvidia-geforce-rtx-3090","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,383.4,null,null],["nvidia-geforce-rtx-3090","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,169.3,null,null],["nvidia-geforce-rtx-3090","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,1155.9,null,null],["nvidia-geforce-rtx-3090","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,1155.9,null,null],["nvidia-geforce-rtx-3090","lfm2-8b-a1b","cuda","fits","F16",8192,17.73,128000,false,290.7,null,null],["nvidia-geforce-rtx-3090","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,177.5,null,null],["nvidia-geforce-rtx-3090","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3090","llama-3-1-70b-instruct","cuda","tight","IQ2_M",8192,27.11,null,null,null,null,null],["nvidia-geforce-rtx-3090","llama-3-1-8b-instruct","cuda","fits","BF16",8192,17.05,41728,false,58.2,null,null],["nvidia-geforce-rtx-3090","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,341.6,null,null],["nvidia-geforce-rtx-3090","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,121088,false,127.1,null,null],["nvidia-geforce-rtx-3090","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"2",null],["nvidia-geforce-rtx-3090","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"3",null],["nvidia-geforce-rtx-3090","mathform-8b","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,116.3,null,null],["nvidia-geforce-rtx-3090","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q8_0",8192,14.03,131072,false,370.7,null,null],["nvidia-geforce-rtx-3090","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,131072,false,445.3,null,null],["nvidia-geforce-rtx-3090","mellum2-12b-a2-5b-instruct","cuda","fits","Q8_0",8192,14.03,131072,false,370.7,null,null],["nvidia-geforce-rtx-3090","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,131072,false,445.3,null,null],["nvidia-geforce-rtx-3090","mellum2-12b-a2-5b-thinking","cuda","fits","Q8_0",8192,14.03,131072,false,370.7,null,null],["nvidia-geforce-rtx-3090","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,131072,false,445.3,null,null],["nvidia-geforce-rtx-3090","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,98816,false,134.6,null,null],["nvidia-geforce-rtx-3090","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"5",null],["nvidia-geforce-rtx-3090","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3090","mimo-v2-6-distill-qwen-9b","cuda","fits","BF16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8",null],["nvidia-geforce-rtx-3090","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8",null],["nvidia-geforce-rtx-3090","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3090","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3090","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"6",null],["nvidia-geforce-rtx-3090","minicpm-o-4-5","cuda","fits","F16",8192,17.34,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,582.8,null,null],["nvidia-geforce-rtx-3090","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,582.8,null,null],["nvidia-geforce-rtx-3090","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,582.8,null,null],["nvidia-geforce-rtx-3090","minicpm-v-4-7-35b-a3b","cuda","fits","Q4_0",8192,20.97,29184,false,460.6,null,null],["nvidia-geforce-rtx-3090","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,1013.5,null,null],["nvidia-geforce-rtx-3090","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,1013.5,null,null],["nvidia-geforce-rtx-3090","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,1013.5,null,null],["nvidia-geforce-rtx-3090","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,192.9,null,null],["nvidia-geforce-rtx-3090","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,262144,true,425.8,null,null],["nvidia-geforce-rtx-3090","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"2",null],["nvidia-geforce-rtx-3090","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"4",null],["nvidia-geforce-rtx-3090","ministral-3-14b-instruct-2512","cuda","fits","Q8_0",8192,15.97,41728,false,62.5,null,null],["nvidia-geforce-rtx-3090","ministral-3-14b-reasoning-2512","cuda","fits","Q8_0",8192,15.97,41728,false,62.5,null,null],["nvidia-geforce-rtx-3090","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,126208,false,121.1,null,null],["nvidia-geforce-rtx-3090","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,126208,false,121.1,null,null],["nvidia-geforce-rtx-3090","ministral-3-8b-instruct-2512","cuda","fits","BF16",8192,17.99,33024,false,54.9,null,null],["nvidia-geforce-rtx-3090","ministral-3-8b-reasoning-2512","cuda","fits","BF16",8192,17.99,33024,false,54.9,null,null],["nvidia-geforce-rtx-3090","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,135.5,null,null],["nvidia-geforce-rtx-3090","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3090","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"3",null],["nvidia-geforce-rtx-3090","mistral-nemo-instruct-2407","cuda","fits","Q8_0",8192,14.65,49664,false,68.6,null,null],["nvidia-geforce-rtx-3090","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q6_K",8192,21.01,10752,false,46.5,null,null],["nvidia-geforce-rtx-3090","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"2",null],["nvidia-geforce-rtx-3090","muse-glimmer-30b","cuda","fits","Q5_K_M",8192,20.66,58368,false,48.4,null,null],["nvidia-geforce-rtx-3090","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3090","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,269.5,null,null],["nvidia-geforce-rtx-3090","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","tight","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-geforce-rtx-3090","nemotron-cascade-14b-thinking","cuda","fits","Q8_0",8192,17.21,32768,false,57.7,null,null],["nvidia-geforce-rtx-3090","nemotron-cascade-2-30b-a3b","cuda","fits","Q4_0",8192,19.24,262144,false,408.4,null,null],["nvidia-geforce-rtx-3090","nemotron-cascade-8b","cuda","fits","BF16",8192,17.35,32768,false,57.3,null,null],["nvidia-geforce-rtx-3090","nemotron-cascade-8b-thinking","cuda","fits","BF16",8192,17.35,32768,false,57.3,null,null],["nvidia-geforce-rtx-3090","nemotron-orchestrator-8b","cuda","fits","BF16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","nemotron-terminal-14b","cuda","fits","Q6_K",8192,13.89,40960,false,73,null,null],["nvidia-geforce-rtx-3090","nemotron-terminal-32b","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,40960,false,126.2,null,null],["nvidia-geforce-rtx-3090","north-mini-code-1-0","cuda","fits","Q4_K_M",8192,20.73,14848,false,334.6,null,null],["nvidia-geforce-rtx-3090","nouscoder-14b","cuda","fits","Q8_0",8192,17.21,34048,false,57.7,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","fits","Q4_0",8192,19.03,262144,false,450.5,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.27,262144,false,408.1,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"4",null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.18,262144,false,419,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,262144,false,128.9,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"3",null],["nvidia-geforce-rtx-3090","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"3",null],["nvidia-geforce-rtx-3090","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.03,262144,false,450.5,null,null],["nvidia-geforce-rtx-3090","nvidia-nemotron-nano-9b-v2","cuda","fits","BF16",8192,18.26,131072,false,55.9,null,null],["nvidia-geforce-rtx-3090","olmo-3-1-32b-instruct","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-1-32b-instruct-dpo","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-1-32b-think","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-1-7b-rl-zero-math","cuda","fits","F16",8192,19.01,12800,false,56.9,null,null],["nvidia-geforce-rtx-3090","olmo-3-1125-32b","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-32b-think","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-32b-think-dpo","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-32b-think-sft","cuda","fits","Q4_0",8192,21.1,9472,false,48.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-instruct","cuda","fits","BF16",8192,19.01,12800,false,56.9,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-think","cuda","fits","BF16",8192,19.01,12800,false,56.9,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,61952,false,112.3,null,null],["nvidia-geforce-rtx-3090","olmocr-2-7b-1025","cuda","fits","BF16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","optimind-sft","cuda","fits","Q5_K_M",8192,17.77,131072,false,291.1,null,null],["nvidia-geforce-rtx-3090","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,41984,false,130.4,null,null],["nvidia-geforce-rtx-3090","phi-4","cuda","fits","Q8_0",8192,17.66,16384,false,56,null,null],["nvidia-geforce-rtx-3090","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,95744,false,107,null,null],["nvidia-geforce-rtx-3090","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"2",null],["nvidia-geforce-rtx-3090","qwen2-5-14b-instruct","cuda","fits","Q8_0",8192,17.48,28416,false,56.8,null,null],["nvidia-geforce-rtx-3090","qwen2-5-32b-instruct","cuda","fits","Q4_0",8192,21.27,8704,false,46,null,null],["nvidia-geforce-rtx-3090","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,261.3,null,null],["nvidia-geforce-rtx-3090","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"2",null],["nvidia-geforce-rtx-3090","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,117.2,null,null],["nvidia-geforce-rtx-3090","qwen2-5-coder-32b-instruct","cuda","fits","Q4_0",8192,21.27,8704,false,46,null,null],["nvidia-geforce-rtx-3090","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,117.2,null,null],["nvidia-geforce-rtx-3090","qwen2-5-vl-7b-instruct","cuda","fits","BF16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","qwen2-5-vl-7b-surg-cholect50","cuda","fits","F16",8192,15.65,107520,false,64.1,null,null],["nvidia-geforce-rtx-3090","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,439.1,null,null],["nvidia-geforce-rtx-3090","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,213.7,null,null],["nvidia-geforce-rtx-3090","qwen3-14b","cuda","fits","Q8_0",8192,17.21,34048,false,57.7,null,null],["nvidia-geforce-rtx-3090","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8",null],["nvidia-geforce-rtx-3090","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"5",null],["nvidia-geforce-rtx-3090","qwen3-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","qwen3-30b-a3b-instruct-2507","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","qwen3-32b","cuda","tight","Q5_K_M",8192,25.66,null,null,null,null,null],["nvidia-geforce-rtx-3090","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,170.7,null,null],["nvidia-geforce-rtx-3090","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,582.7,null,null],["nvidia-geforce-rtx-3090","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1301,null,null],["nvidia-geforce-rtx-3090","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"2",null],["nvidia-geforce-rtx-3090","qwen3-5-27b","cuda","fits","Q5_K_M",8192,21.01,14592,false,48.6,null,null],["nvidia-geforce-rtx-3090","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,242.1,null,null],["nvidia-geforce-rtx-3090","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,568.6,null,null],["nvidia-geforce-rtx-3090","qwen3-5-35b-a3b","cuda","fits","Q3_K_M",8192,17.55,184064,false,359.2,null,null],["nvidia-geforce-rtx-3090","qwen3-5-35b-a3b-base","cuda","fits","Q4_0",8192,21.06,25344,false,459.8,null,null],["nvidia-geforce-rtx-3090","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090","qwen3-5-4b","cuda","fits","BF16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","qwen3-5-9b","cuda","fits","BF16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","qwen3-5-9b-base","cuda","fits","F16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","qwen3-6-27b","cuda","fits","Q5_K_M",8192,20.92,15872,false,48.8,null,null],["nvidia-geforce-rtx-3090","qwen3-6-35b-a3b","cuda","fits","Q4_0",8192,21.19,19200,false,430.4,null,null],["nvidia-geforce-rtx-3090","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3090","qwen3-8-27b","cuda","fits","Q4_K_M",8192,18.81,47616,false,55,null,null],["nvidia-geforce-rtx-3090","qwen3-8-3-6-27b-blend","cuda","fits","Q4_K_M",8192,18.81,47616,false,55,null,null],["nvidia-geforce-rtx-3090","qwen3-8b","cuda","fits","Q8_0",8192,10.39,40960,false,101.2,null,null],["nvidia-geforce-rtx-3090","qwen3-coder-30b-a3b-instruct","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"2",null],["nvidia-geforce-rtx-3090","qwen3-coder-next-base","cuda","tight","IQ2_M",8192,27.24,null,null,null,null,null],["nvidia-geforce-rtx-3090","qwen3-coder-reap-25b-a3b","cuda","fits","Q5_K_M",8192,19.26,30208,false,308.6,null,null],["nvidia-geforce-rtx-3090","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8",null],["nvidia-geforce-rtx-3090","qwen3-nemotron-14b-brrm","cuda","fits","Q6_K",8192,13.89,40960,false,73,null,null],["nvidia-geforce-rtx-3090","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,40960,false,126.2,null,null],["nvidia-geforce-rtx-3090","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"2",null],["nvidia-geforce-rtx-3090","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"5",null],["nvidia-geforce-rtx-3090","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-30b-a3b-instruct","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-32b-instruct","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-32b-thinking","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-8b-instruct","cuda","fits","BF16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","qwen3-vl-8b-thinking","cuda","fits","BF16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","qwq-32b","cuda","tight","Q5_K_M",8192,25.7,null,null,null,null,null],["nvidia-geforce-rtx-3090","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,195.5,null,null],["nvidia-geforce-rtx-3090","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,95744,false,126.2,null,null],["nvidia-geforce-rtx-3090","rnj-1-instruct","cuda","fits","BF16",8192,18.63,29696,false,52.9,null,null],["nvidia-geforce-rtx-3090","sera-32b","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","singguard-2b","cuda","fits","F16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,138.6,null,null],["nvidia-geforce-rtx-3090","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,299.3,null,null],["nvidia-geforce-rtx-3090","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"2",null],["nvidia-geforce-rtx-3090","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,128000,false,149.3,null,null],["nvidia-geforce-rtx-3090","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,83456,false,101.2,null,null],["nvidia-geforce-rtx-3090","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"3",null],["nvidia-geforce-rtx-3090","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"2",null],["nvidia-geforce-rtx-3090","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"3",null],["nvidia-geforce-rtx-3090","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"5",null],["nvidia-geforce-rtx-3090","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,40960,false,126.2,null,null],["nvidia-geforce-rtx-3090","tiny-aya-earth","cuda","fits","BF16",8192,8.72,262144,true,132.3,null,null],["nvidia-geforce-rtx-3090","tiny-aya-fire","cuda","fits","BF16",8192,8.72,262144,true,132.3,null,null],["nvidia-geforce-rtx-3090","tiny-aya-global","cuda","fits","BF16",8192,8.72,262144,true,132.3,null,null],["nvidia-geforce-rtx-3090","tiny-aya-water","cuda","fits","BF16",8192,8.72,262144,true,132.3,null,null],["nvidia-geforce-rtx-3090","translategemma-12b-it","cuda","fits","Q8_0",8192,15.82,92928,false,70,null,null],["nvidia-geforce-rtx-3090","translategemma-27b-it","cuda","fits","Q4_K_M",8192,20.35,21248,false,53,null,null],["nvidia-geforce-rtx-3090","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,116.3,null,null],["nvidia-geforce-rtx-3090","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["nvidia-geforce-rtx-3090","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"6",null],["nvidia-geforce-rtx-3090","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["nvidia-geforce-rtx-3090","trinity-mini","cuda","fits","Q5_K_M",8192,19.95,89088,false,368,null,null],["nvidia-geforce-rtx-3090","trinity-mini-base","cuda","fits","Q5_K_M",8192,19.87,93440,false,379.9,null,null],["nvidia-geforce-rtx-3090","trinity-mini-base-pre-anneal","cuda","fits","Q5_K_M",4096,19.59,4096,false,390.5,null,null],["nvidia-geforce-rtx-3090","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,1039.3,null,null],["nvidia-geforce-rtx-3090","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,1111.8,null,null],["nvidia-geforce-rtx-3090","trinity-nano-preview","cuda","fits","BF16",8192,13.51,131072,false,503.8,null,null],["nvidia-geforce-rtx-3090","ui-mate-27b","cuda","fits","Q4_K_M",8192,19.13,42752,false,54,null,null],["nvidia-geforce-rtx-3090","ui-mate-9b","cuda","fits","BF16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","ui-mate-democua-27b","cuda","fits","Q5_K_M",8192,20.64,19968,false,49.6,null,null],["nvidia-geforce-rtx-3090","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","ui-venus-1-5-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,21504,false,343.5,null,null],["nvidia-geforce-rtx-3090","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,95744,false,126.2,null,null],["nvidia-geforce-rtx-3090","ui-venus-2-9b","cuda","fits","BF16",8192,17.55,122112,false,58,null,null],["nvidia-geforce-rtx-3090","userrepgen-4b","cuda","fits","BF16",8192,10.23,262144,false,107.8,null,null],["nvidia-geforce-rtx-3090","webworld-14b","cuda","fits","Q6_K",8192,13.89,40960,false,73,null,null],["nvidia-geforce-rtx-3090","webworld-32b","cuda","fits","Q4_0",8192,21.33,8448,false,45.9,null,null],["nvidia-geforce-rtx-3090","webworld-8b","cuda","fits","F16",8192,17.35,36096,false,57.3,null,null],["nvidia-geforce-rtx-3090","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,128000,false,149.3,null,null],["nvidia-geforce-rtx-3090","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,487.5,null,null],["nvidia-geforce-rtx-3090","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,487.5,null,null],["nvidia-geforce-rtx-3090","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,212,null,null],["nvidia-geforce-rtx-3090","zwz-2b","cuda","fits","F16",8192,5.62,146432,false,213.7,null,null],["nvidia-geforce-rtx-3090","zwz-4b","cuda","fits","Q6_K",8192,5.74,115200,false,207.6,null,null],["nvidia-geforce-rtx-3090","zwz-7b","cuda","fits","Q6_K",8192,7.47,128000,false,149.3,null,null],["nvidia-geforce-rtx-3090","zwz-8b","cuda","fits","Q6_K",8192,8.59,95744,false,126.2,null,null],["nvidia-geforce-rtx-3090-ti","aescode-32b","cuda","fits","IQ4_XS",8192,20.78,8448,false,50.8,null,null],["nvidia-geforce-rtx-3090-ti","aescode-8b","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,111360,false,223.6,null,null],["nvidia-geforce-rtx-3090-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,166,null,null],["nvidia-geforce-rtx-3090-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,166,null,null],["nvidia-geforce-rtx-3090-ti","ai21-jamba2-mini","cuda","fits","Q2_K",8192,19.01,111104,false,228.8,null,null],["nvidia-geforce-rtx-3090-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,385.1,null,null],["nvidia-geforce-rtx-3090-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,385.1,null,null],["nvidia-geforce-rtx-3090-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,313.9,null,null],["nvidia-geforce-rtx-3090-ti","apriel-1-6-15b-thinker","cuda","fits","Q8_0",8192,17.19,26880,false,62.1,null,null],["nvidia-geforce-rtx-3090-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,131072,false,149.9,null,null],["nvidia-geforce-rtx-3090-ti","armorocr","cuda","fits","Q8_0",8192,10.39,79616,false,109,null,null],["nvidia-geforce-rtx-3090-ti","astabrief-8b","cuda","fits","Q6_K",8192,8.59,40960,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","autoglm-phone-9b","cuda","fits","F16",8192,18.87,55808,false,56.3,null,null],["nvidia-geforce-rtx-3090-ti","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,124.7,null,null],["nvidia-geforce-rtx-3090-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","bielik-11b-v3-0-instruct","cuda","fits","Q8_0",8192,14.42,32768,false,75.2,null,null],["nvidia-geforce-rtx-3090-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,32768,false,110.2,null,null],["nvidia-geforce-rtx-3090-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,328.1,null,null],["nvidia-geforce-rtx-3090-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","contextpilot-14b","cuda","fits","Q8_0",8192,17.21,30720,false,62.2,null,null],["nvidia-geforce-rtx-3090-ti","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,40960,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","contextpilot-e4b","cuda","fits","F16",8192,10.89,131072,false,106.7,null,null],["nvidia-geforce-rtx-3090-ti","cosmos-reason2-32b","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,91904,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,182.3,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-distill-llama-8b","cuda","fits","BF16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-distill-qwen-14b","cuda","fits","Q8_0",8192,17.48,25600,false,61.2,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-distill-qwen-32b","cuda","fits","Q3_K_M",8192,18.71,16384,false,56.8,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-r1-distill-qwen-7b","cuda","fits","F16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","devstral-small-2-24b-instruct-2512","cuda","fits","Q5_K_M",8192,18.57,22272,false,57.2,null,null],["nvidia-geforce-rtx-3090-ti","eurollm-22b-2512","cuda","fits","Q6_K",8192,20.63,9216,false,51.1,null,null],["nvidia-geforce-rtx-3090-ti","eurollm-22b-instruct-2512","cuda","fits","Q6_K",8192,20.63,9216,false,51.1,null,null],["nvidia-geforce-rtx-3090-ti","eurollm-9b-instruct-2512","cuda","fits","F16",8192,19.58,15616,false,54,null,null],["nvidia-geforce-rtx-3090-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1639.9,null,null],["nvidia-geforce-rtx-3090-ti","exaone-4-5-33b","cuda","fits","IQ4_XS",8192,20.43,9728,false,54,null,null],["nvidia-geforce-rtx-3090-ti","fara-7b","cuda","fits","BF16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","fara1-5-27b","cuda","fits","Q4_K_M",8192,19.13,34304,false,58.1,null,null],["nvidia-geforce-rtx-3090-ti","fara1-5-4b","cuda","fits","BF16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","fara1-5-9b","cuda","fits","BF16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","frogboss-32b-2510","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","frogmini-14b-2510","cuda","fits","Q6_K",8192,13.89,40960,false,78.6,null,null],["nvidia-geforce-rtx-3090-ti","frognano-4b-2609","cuda","fits","BF16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1770.5,null,null],["nvidia-geforce-rtx-3090-ti","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","gemma-2-27b-it","cuda","fits","IQ4_XS",8192,19.09,8192,false,58.9,null,null],["nvidia-geforce-rtx-3090-ti","gemma-2-9b-it","cuda","fits","Q8_0",8192,14.78,8192,false,78.8,null,null],["nvidia-geforce-rtx-3090-ti","gemma-3-12b-it","cuda","fits","Q8_0",8192,15.82,84480,false,75.4,null,null],["nvidia-geforce-rtx-3090-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,492.9,null,null],["nvidia-geforce-rtx-3090-ti","gemma-3-27b-it","cuda","fits","Q4_K_M",8192,20.35,14336,false,57.1,null,null],["nvidia-geforce-rtx-3090-ti","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-12b","cuda","fits","Q8_0",8192,15.57,262144,false,76.8,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-12b-it","cuda","fits","Q8_0",8192,15.57,262144,false,76.8,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-26b-a4b","cuda","fits","Q4_K_M",8192,19.09,88832,false,339,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-26b-a4b-it","cuda","fits","Q4_K_M",8192,19.33,78080,false,313.8,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-31b","cuda","fits","Q2_K",8192,17.58,48128,false,75.2,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-31b-it","cuda","fits","Q3_K_M",8192,20.34,14592,false,62.1,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,514.4,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,216.6,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-e4b","cuda","fits","F16",8192,11,131072,false,105.5,null,null],["nvidia-geforce-rtx-3090-ti","gemma-4-e4b-it","cuda","fits","BF16",8192,11,131072,false,105.5,null,null],["nvidia-geforce-rtx-3090-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","glm-4-6v-flash","cuda","fits","BF16",8192,18.87,55808,false,56.3,null,null],["nvidia-geforce-rtx-3090-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","glm-4-7-flash","cuda","fits","Q4_K_M",8192,19.53,32512,false,354.2,null,null],["nvidia-geforce-rtx-3090-ti","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q6_K",8192,20.11,21760,false,288.4,null,null],["nvidia-geforce-rtx-3090-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","gpt-oss-20b","cuda","fits","Q8_0",8192,12.9,131072,false,362.7,null,null],["nvidia-geforce-rtx-3090-ti","granite-3-3-8b-instruct","cuda","fits","F16",8192,18.62,22016,false,57,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,131072,false,256.2,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,1072.6,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,336.9,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1410,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-1-30b","cuda","fits","Q4_K_M",8192,20.53,9472,false,51.3,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-1-3b","cuda","fits","BF16",8192,8.61,131072,false,134.8,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-1-8b","cuda","fits","BF16",8192,19.03,19456,false,55.7,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-2-30b","cuda","fits","Q4_K_M",8192,20.53,9472,false,51.3,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-2-3b","cuda","fits","BF16",8192,8.61,131072,false,134.8,null,null],["nvidia-geforce-rtx-3090-ti","granite-4-2-8b","cuda","fits","BF16",8192,19.03,19456,false,55.7,null,null],["nvidia-geforce-rtx-3090-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","F16",8192,18.62,22016,false,57,null,null],["nvidia-geforce-rtx-3090-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,131072,false,291.1,null,null],["nvidia-geforce-rtx-3090-ti","granite-guardian-4-1-8b","cuda","fits","BF16",8192,19.03,19456,false,55.7,null,null],["nvidia-geforce-rtx-3090-ti","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,131072,false,134.8,null,null],["nvidia-geforce-rtx-3090-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,103936,false,139.4,null,null],["nvidia-geforce-rtx-3090-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,160.7,null,null],["nvidia-geforce-rtx-3090-ti","hermes-4-3-36b","cuda","fits","Q3_K_M",8192,20.37,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,428.7,null,null],["nvidia-geforce-rtx-3090-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1401.1,null,null],["nvidia-geforce-rtx-3090-ti","holo-3-1-35b-a3b","cuda","fits","IQ4_XS",8192,20.23,37376,false,493,null,null],["nvidia-geforce-rtx-3090-ti","holo-3-1-4b","cuda","fits","F16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","holo-3-1-9b","cuda","fits","F16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","holo2-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","holo2-4b","cuda","fits","F16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","holo2-8b","cuda","fits","Q6_K",8192,8.59,91904,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","holo3-35b-a3b","cuda","fits","IQ4_XS",8192,20.23,37376,false,493,null,null],["nvidia-geforce-rtx-3090-ti","holo4-27b","cuda","fits","Q5_K_M",8192,20.64,11520,false,53.4,null,null],["nvidia-geforce-rtx-3090-ti","holo4-35b-a3b","cuda","fits","Q3_K_M",8192,18.4,120064,false,383.3,null,null],["nvidia-geforce-rtx-3090-ti","holotron4-30b-a3b","cuda","fits","Q4_0",8192,19.03,238336,false,485.2,null,null],["nvidia-geforce-rtx-3090-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,535.2,null,null],["nvidia-geforce-rtx-3090-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","F16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","F16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","F16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","F16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,40960,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,40960,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,40960,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,40960,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"7",null],["nvidia-geforce-rtx-3090-ti","ising-calibration-1-35b-a3b","cuda","fits","IQ4_XS",8192,20.02,46592,false,494.7,null,null],["nvidia-geforce-rtx-3090-ti","ising-calibration-1-5-31b-bf16","cuda","fits","IQ3_XXS",8192,18.62,35328,false,69.6,null,null],["nvidia-geforce-rtx-3090-ti","januscoder-14b","cuda","fits","Q8_0",8192,17.21,30720,false,62.2,null,null],["nvidia-geforce-rtx-3090-ti","januscoder-8b","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","januscoderv-7b","cuda","fits","BF16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,273.7,null,null],["nvidia-geforce-rtx-3090-ti","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,135.6,null,null],["nvidia-geforce-rtx-3090-ti","kat-coder-v2-5-dev","cuda","fits","IQ4_XS",8192,20.1,43264,false,476.6,null,null],["nvidia-geforce-rtx-3090-ti","kat-dev-72b-exp","cuda","tight","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","kimi-linear-48b-a3b-base","cuda","fits","IQ3_XXS",8192,20.04,92416,false,710.4,null,null],["nvidia-geforce-rtx-3090-ti","kimi-linear-48b-a3b-instruct","cuda","fits","IQ3_XXS",8192,20.69,27136,false,585.8,null,null],["nvidia-geforce-rtx-3090-ti","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ4_XS",8192,19.84,112896,false,540.2,null,null],["nvidia-geforce-rtx-3090-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090-ti","laguna-xs-2-1","cuda","fits","Q4_0",8192,20.64,13824,false,436.4,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,191.2,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,191.2,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,191.2,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-24b-a2b","cuda","fits","Q6_K",8192,20.64,18944,false,481.5,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,182.3,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,429.4,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1799.5,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-24b-a2b","cuda","fits","Q6_K",8192,20.74,14080,false,458.5,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,1244.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-8b-a1b","cuda","fits","BF16",8192,17.99,128000,false,290,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,2573.7,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,412.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,182.3,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,1244.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,1244.8,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-8b-a1b","cuda","fits","F16",8192,17.73,128000,false,313.1,null,null],["nvidia-geforce-rtx-3090-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,191.2,null,null],["nvidia-geforce-rtx-3090-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","llama-3-1-70b-instruct","cuda","tight","IQ2_M",8192,27.11,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","llama-3-1-8b-instruct","cuda","fits","BF16",8192,17.05,37376,false,62.7,null,null],["nvidia-geforce-rtx-3090-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,367.9,null,null],["nvidia-geforce-rtx-3090-ti","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,116224,false,136.9,null,null],["nvidia-geforce-rtx-3090-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","mathform-8b","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q8_0",8192,14.03,131072,false,399.2,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,131072,false,479.5,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q8_0",8192,14.03,131072,false,399.2,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,131072,false,479.5,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q8_0",8192,14.03,131072,false,399.2,null,null],["nvidia-geforce-rtx-3090-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,131072,false,479.5,null,null],["nvidia-geforce-rtx-3090-ti","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,94976,false,145,null,null],["nvidia-geforce-rtx-3090-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","BF16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","minicpm-o-4-5","cuda","fits","F16",8192,17.34,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,627.7,null,null],["nvidia-geforce-rtx-3090-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,627.7,null,null],["nvidia-geforce-rtx-3090-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,627.7,null,null],["nvidia-geforce-rtx-3090-ti","minicpm-v-4-7-35b-a3b","cuda","fits","IQ4_XS",8192,20.02,46592,false,494.8,null,null],["nvidia-geforce-rtx-3090-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,1091.5,null,null],["nvidia-geforce-rtx-3090-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,1091.5,null,null],["nvidia-geforce-rtx-3090-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,1091.5,null,null],["nvidia-geforce-rtx-3090-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,207.8,null,null],["nvidia-geforce-rtx-3090-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,262144,true,458.6,null,null],["nvidia-geforce-rtx-3090-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","ministral-3-14b-instruct-2512","cuda","fits","Q8_0",8192,15.97,38144,false,67.3,null,null],["nvidia-geforce-rtx-3090-ti","ministral-3-14b-reasoning-2512","cuda","fits","Q8_0",8192,15.97,38144,false,67.3,null,null],["nvidia-geforce-rtx-3090-ti","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,121088,false,130.4,null,null],["nvidia-geforce-rtx-3090-ti","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,121088,false,130.4,null,null],["nvidia-geforce-rtx-3090-ti","ministral-3-8b-instruct-2512","cuda","fits","BF16",8192,17.99,28928,false,59.1,null,null],["nvidia-geforce-rtx-3090-ti","ministral-3-8b-reasoning-2512","cuda","fits","BF16",8192,17.99,28928,false,59.1,null,null],["nvidia-geforce-rtx-3090-ti","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,145.9,null,null],["nvidia-geforce-rtx-3090-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","mistral-nemo-instruct-2407","cuda","fits","Q8_0",8192,14.65,46336,false,73.9,null,null],["nvidia-geforce-rtx-3090-ti","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q5_K_M",8192,18.57,22272,false,57.2,null,null],["nvidia-geforce-rtx-3090-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","muse-glimmer-30b","cuda","fits","Q5_K_M",8192,20.66,21248,false,52.1,null,null],["nvidia-geforce-rtx-3090-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,290.2,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","tight","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-cascade-14b-thinking","cuda","fits","Q8_0",8192,17.21,30720,false,62.2,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-cascade-2-30b-a3b","cuda","fits","Q4_0",8192,19.24,212224,false,439.8,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-cascade-8b","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-cascade-8b-thinking","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-orchestrator-8b","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-terminal-14b","cuda","fits","Q6_K",8192,13.89,40960,false,78.6,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-terminal-32b","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,40960,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","north-mini-code-1-0","cuda","fits","Q4_K_M",8192,20.73,9472,false,360.3,null,null],["nvidia-geforce-rtx-3090-ti","nouscoder-14b","cuda","fits","Q8_0",8192,17.21,30720,false,62.2,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","fits","Q4_0",8192,19.03,238336,false,485.2,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.27,207360,false,439.5,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.18,219136,false,451.2,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,262144,false,138.8,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","fits","Q4_0",8192,19.03,238336,false,485.2,null,null],["nvidia-geforce-rtx-3090-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","BF16",8192,18.26,131072,false,60.2,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1-32b-instruct","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1-32b-think","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1-7b-rl-zero-math","cuda","fits","F16",8192,19.01,11776,false,61.2,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-1125-32b","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-32b-think","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-32b-think-dpo","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-32b-think-sft","cuda","fits","IQ4_XS",8192,20.12,11008,false,54.8,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-instruct","cuda","fits","BF16",8192,19.01,11776,false,61.2,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-think","cuda","fits","BF16",8192,19.01,11776,false,61.2,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,57600,false,120.9,null,null],["nvidia-geforce-rtx-3090-ti","olmocr-2-7b-1025","cuda","fits","BF16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","optimind-sft","cuda","fits","Q5_K_M",8192,17.77,127232,false,313.5,null,null],["nvidia-geforce-rtx-3090-ti","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,40448,false,140.4,null,null],["nvidia-geforce-rtx-3090-ti","phi-4","cuda","fits","Q8_0",8192,17.66,16384,false,60.3,null,null],["nvidia-geforce-rtx-3090-ti","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,91392,false,115.3,null,null],["nvidia-geforce-rtx-3090-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","qwen2-5-14b-instruct","cuda","fits","Q8_0",8192,17.48,25600,false,61.2,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-32b-instruct","cuda","fits","Q3_K_M",8192,18.71,16384,false,56.8,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,281.4,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,126.3,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-coder-32b-instruct","cuda","fits","Q3_K_M",8192,18.71,16384,false,56.8,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,126.3,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-vl-7b-instruct","cuda","fits","BF16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","F16",8192,15.65,97792,false,69,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,472.8,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-14b","cuda","fits","Q8_0",8192,17.21,30720,false,62.2,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","qwen3-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-30b-a3b-instruct-2507","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-32b","cuda","tight","Q5_K_M",8192,25.66,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,183.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,627.5,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1401.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","qwen3-5-27b","cuda","fits","Q4_K_M",8192,18.36,46080,false,60.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,260.8,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,612.4,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-35b-a3b","cuda","fits","Q3_K_M",8192,17.55,158464,false,386.8,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-35b-a3b-base","cuda","fits","IQ4_XS",8192,19.95,50176,false,514.6,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090-ti","qwen3-5-4b","cuda","fits","BF16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-9b","cuda","fits","BF16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-5-9b-base","cuda","fits","F16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-6-27b","cuda","fits","Q4_K_M",8192,18.43,45056,false,60.6,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-6-35b-a3b","cuda","fits","IQ4_XS",8192,20.09,43520,false,477.7,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-3090-ti","qwen3-8-27b","cuda","fits","Q4_K_M",8192,18.81,39168,false,59.2,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-8-3-6-27b-blend","cuda","fits","Q4_K_M",8192,18.81,39168,false,59.2,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-8b","cuda","fits","Q8_0",8192,10.39,40960,false,109,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-30b-a3b-instruct","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"8:tight",null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-next-base","cuda","tight","IQ2_M",8192,27.24,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-reap-25b-a3b","cuda","fits","Q5_K_M",8192,19.26,24320,false,332.4,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8",null],["nvidia-geforce-rtx-3090-ti","qwen3-nemotron-14b-brrm","cuda","fits","Q6_K",8192,13.89,40960,false,78.6,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"4",null],["nvidia-geforce-rtx-3090-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,40960,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-30b-a3b-instruct","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-32b-instruct","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-32b-thinking","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-8b-instruct","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","qwen3-vl-8b-thinking","cuda","fits","BF16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","qwq-32b","cuda","tight","Q5_K_M",8192,25.7,null,null,null,null,null],["nvidia-geforce-rtx-3090-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,210.5,null,null],["nvidia-geforce-rtx-3090-ti","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,91904,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","rnj-1-instruct","cuda","fits","BF16",8192,18.63,25344,false,57,null,null],["nvidia-geforce-rtx-3090-ti","sera-32b","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","singguard-2b","cuda","fits","F16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,149.2,null,null],["nvidia-geforce-rtx-3090-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,322.4,null,null],["nvidia-geforce-rtx-3090-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,128000,false,160.7,null,null],["nvidia-geforce-rtx-3090-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,79616,false,108.9,null,null],["nvidia-geforce-rtx-3090-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"2",null],["nvidia-geforce-rtx-3090-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"3",null],["nvidia-geforce-rtx-3090-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"5",null],["nvidia-geforce-rtx-3090-ti","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,40960,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","tiny-aya-earth","cuda","fits","BF16",8192,8.72,262144,true,142.5,null,null],["nvidia-geforce-rtx-3090-ti","tiny-aya-fire","cuda","fits","BF16",8192,8.72,262144,true,142.5,null,null],["nvidia-geforce-rtx-3090-ti","tiny-aya-global","cuda","fits","BF16",8192,8.72,262144,true,142.5,null,null],["nvidia-geforce-rtx-3090-ti","tiny-aya-water","cuda","fits","BF16",8192,8.72,262144,true,142.5,null,null],["nvidia-geforce-rtx-3090-ti","translategemma-12b-it","cuda","fits","Q8_0",8192,15.82,84480,false,75.4,null,null],["nvidia-geforce-rtx-3090-ti","translategemma-27b-it","cuda","fits","Q4_K_M",8192,20.35,14336,false,57.1,null,null],["nvidia-geforce-rtx-3090-ti","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,125.2,null,null],["nvidia-geforce-rtx-3090-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"6",null],["nvidia-geforce-rtx-3090-ti","trinity-mini","cuda","fits","Q5_K_M",8192,19.95,57856,false,396.3,null,null],["nvidia-geforce-rtx-3090-ti","trinity-mini-base","cuda","fits","Q5_K_M",8192,19.87,62208,false,409.1,null,null],["nvidia-geforce-rtx-3090-ti","trinity-mini-base-pre-anneal","cuda","fits","Q5_K_M",4096,19.59,4096,false,420.5,null,null],["nvidia-geforce-rtx-3090-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,1119.3,null,null],["nvidia-geforce-rtx-3090-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,1197.3,null,null],["nvidia-geforce-rtx-3090-ti","trinity-nano-preview","cuda","fits","BF16",8192,13.51,131072,false,542.5,null,null],["nvidia-geforce-rtx-3090-ti","ui-mate-27b","cuda","fits","Q4_K_M",8192,19.13,34304,false,58.1,null,null],["nvidia-geforce-rtx-3090-ti","ui-mate-9b","cuda","fits","BF16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","ui-mate-democua-27b","cuda","fits","Q5_K_M",8192,20.64,11520,false,53.4,null,null],["nvidia-geforce-rtx-3090-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","ui-venus-1-5-30b-a3b","cuda","fits","Q4_K_M",8192,20.13,15616,false,369.9,null,null],["nvidia-geforce-rtx-3090-ti","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,91904,false,135.9,null,null],["nvidia-geforce-rtx-3090-ti","ui-venus-2-9b","cuda","fits","BF16",8192,17.55,105472,false,62.4,null,null],["nvidia-geforce-rtx-3090-ti","userrepgen-4b","cuda","fits","BF16",8192,10.23,262144,false,116.1,null,null],["nvidia-geforce-rtx-3090-ti","webworld-14b","cuda","fits","Q6_K",8192,13.89,40960,false,78.6,null,null],["nvidia-geforce-rtx-3090-ti","webworld-32b","cuda","fits","IQ4_XS",8192,20.36,9984,false,51.9,null,null],["nvidia-geforce-rtx-3090-ti","webworld-8b","cuda","fits","F16",8192,17.35,32256,false,61.7,null,null],["nvidia-geforce-rtx-3090-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,128000,false,160.7,null,null],["nvidia-geforce-rtx-3090-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,525,null,null],["nvidia-geforce-rtx-3090-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,525,null,null],["nvidia-geforce-rtx-3090-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,228.3,null,null],["nvidia-geforce-rtx-3090-ti","zwz-2b","cuda","fits","F16",8192,5.62,141312,false,230.1,null,null],["nvidia-geforce-rtx-3090-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,111360,false,223.6,null,null],["nvidia-geforce-rtx-3090-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,128000,false,160.7,null,null],["nvidia-geforce-rtx-3090-ti","zwz-8b","cuda","fits","Q6_K",8192,8.59,91904,false,135.9,null,null],["nvidia-geforce-rtx-4060","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"5",null],["nvidia-geforce-rtx-4060","aescode-8b","cuda","tight","Q6_K",8192,9,null,null,null,null,null],["nvidia-geforce-rtx-4060","agentcpm-explore","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,135168,false,84,null,null],["nvidia-geforce-rtx-4060","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,135168,false,84,null,null],["nvidia-geforce-rtx-4060","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-4060","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,103.9,null,null],["nvidia-geforce-rtx-4060","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,103.9,null,null],["nvidia-geforce-rtx-4060","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,84.7,null,null],["nvidia-geforce-rtx-4060","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","aprielguard","cuda","fits","IQ2_M",8192,4.68,9984,false,78.3,null,null],["nvidia-geforce-rtx-4060","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-4060","astabrief-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","autoglm-phone-9b","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","autoglm-phone-9b-multilingual","cuda","fits","IQ2_XXS",8192,4.82,9472,false,76.3,null,null],["nvidia-geforce-rtx-4060","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4060","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-4060","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,25088,false,88.5,null,null],["nvidia-geforce-rtx-4060","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","caprl-qwen3vl-4b","cuda","fits","Q2_K",8192,4.14,13056,false,94.7,null,null],["nvidia-geforce-rtx-4060","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4060","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-4060","contextpilot-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","contextpilot-e4b","cuda","fits","Q4_K_M",8192,4.7,17920,false,86.9,null,null],["nvidia-geforce-rtx-4060","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-4060","cosmos-reason2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,90.6,null,null],["nvidia-geforce-rtx-4060","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4060","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","deepseek-r1-distill-llama-8b","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-4060","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-4060","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-4060","deepseek-r1-distill-qwen-7b","cuda","fits","Q2_K",8192,4.56,13568,false,82.4,null,null],["nvidia-geforce-rtx-4060","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4060","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4060","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4060","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-4060","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-4060","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-4060","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-4060","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,442.5,null,null],["nvidia-geforce-rtx-4060","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"7",null],["nvidia-geforce-rtx-4060","fara-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-4060","fara1-5-4b","cuda","fits","Q4_K_M",8192,4.8,10240,false,86.6,null,null],["nvidia-geforce-rtx-4060","fara1-5-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-4060","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-4060","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","frognano-4b-2609","cuda","fits","Q4_K_M",8192,4.65,14592,false,91.1,null,null],["nvidia-geforce-rtx-4060","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,477.7,null,null],["nvidia-geforce-rtx-4060","gelab-zero-4b-preview","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"5",null],["nvidia-geforce-rtx-4060","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-4060","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-4060","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,133,null,null],["nvidia-geforce-rtx-4060","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-4060","gemma-3-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,98.1,null,null],["nvidia-geforce-rtx-4060","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-4060","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-4060","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-4060","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"4",null],["nvidia-geforce-rtx-4060","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"7",null],["nvidia-geforce-rtx-4060","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"7",null],["nvidia-geforce-rtx-4060","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,138.8,null,null],["nvidia-geforce-rtx-4060","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,102656,false,104.9,null,null],["nvidia-geforce-rtx-4060","gemma-4-e4b","cuda","fits","Q4_K_M",8192,4.73,16128,false,86,null,null],["nvidia-geforce-rtx-4060","gemma-4-e4b-it","cuda","fits","Q4_K_M",8192,4.75,15104,false,85.6,null,null],["nvidia-geforce-rtx-4060","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","glm-4-6v-flash","cuda","tight","Q6_K",8192,9.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-4060","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4060","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-4060","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"4",null],["nvidia-geforce-rtx-4060","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-4060","granite-4-0-1b","cuda","fits","Q8_0",8192,3.64,23040,false,113.1,null,null],["nvidia-geforce-rtx-4060","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,289.4,null,null],["nvidia-geforce-rtx-4060","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,51456,false,90.9,null,null],["nvidia-geforce-rtx-4060","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,380.5,null,null],["nvidia-geforce-rtx-4060","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-4060","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,10496,false,78.5,null,null],["nvidia-geforce-rtx-4060","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-4060","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-4060","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,10496,false,78.5,null,null],["nvidia-geforce-rtx-4060","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-4060","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-4060","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,10496,false,78.5,null,null],["nvidia-geforce-rtx-4060","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-4060","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,10496,false,78.5,null,null],["nvidia-geforce-rtx-4060","harc-llama-3-1-8b-instruct","cuda","fits","IQ2_XXS",8192,4.51,10752,false,82.6,null,null],["nvidia-geforce-rtx-4060","harc-qwen2-5-7b-instruct","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"4",null],["nvidia-geforce-rtx-4060","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,18944,false,115.7,null,null],["nvidia-geforce-rtx-4060","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,191232,false,378.1,null,null],["nvidia-geforce-rtx-4060","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-4060","holo-3-1-4b","cuda","fits","Q4_K_M",8192,4.63,15360,false,91.7,null,null],["nvidia-geforce-rtx-4060","holo-3-1-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-4060","holo2-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","holo2-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-4060","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-4060","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"4",null],["nvidia-geforce-rtx-4060","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-4060","hunyuanocr","cuda","fits","F16",8192,3.13,25856,false,144.4,null,null],["nvidia-geforce-rtx-4060","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-4060","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-llama3-8b-baseline","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-llama3-8b-multiview","cuda","tight","Q8_0",8192,10.15,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-4060","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-4060","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"6",null],["nvidia-geforce-rtx-4060","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","januscoderv-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-4060","kanana-2-3b-base","cuda","fits","Q5_K_M",8192,4.57,10496,false,81.1,null,null],["nvidia-geforce-rtx-4060","kanana-2-3b-instruct","cuda","fits","Q5_K_M",8192,4.57,10496,false,81.1,null,null],["nvidia-geforce-rtx-4060","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-4060","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4060","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4060","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4060","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4060","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"5",null],["nvidia-geforce-rtx-4060","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-4060","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-4060","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-4060","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-4060","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,51456,false,94.9,null,null],["nvidia-geforce-rtx-4060","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,51456,false,94.9,null,null],["nvidia-geforce-rtx-4060","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,51456,false,94.9,null,null],["nvidia-geforce-rtx-4060","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-4060","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,44032,false,90.6,null,null],["nvidia-geforce-rtx-4060","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,79616,false,115.9,null,null],["nvidia-geforce-rtx-4060","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,485.6,null,null],["nvidia-geforce-rtx-4060","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-4060","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,335.9,null,null],["nvidia-geforce-rtx-4060","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-4060","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,694.5,null,null],["nvidia-geforce-rtx-4060","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,93440,false,111.4,null,null],["nvidia-geforce-rtx-4060","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,90.6,null,null],["nvidia-geforce-rtx-4060","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,335.9,null,null],["nvidia-geforce-rtx-4060","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,335.9,null,null],["nvidia-geforce-rtx-4060","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-4060","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,51456,false,94.9,null,null],["nvidia-geforce-rtx-4060","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4060","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"7",null],["nvidia-geforce-rtx-4060","llama-3-1-8b-instruct","cuda","tight","Q6_K",8192,8.37,null,null,null,null,null],["nvidia-geforce-rtx-4060","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,34816,false,99.3,null,null],["nvidia-geforce-rtx-4060","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,8960,false,76.1,null,null],["nvidia-geforce-rtx-4060","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","medgemma-1-5-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,98.1,null,null],["nvidia-geforce-rtx-4060","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-4060","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-4060","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-4060","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-4060","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-4060","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-4060","mimo-embodied-7b","cuda","fits","IQ2_XXS",8192,4.6,9984,false,81.4,null,null],["nvidia-geforce-rtx-4060","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-6-distill-qwen-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-4060","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-4060","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","minicpm-v-4-6","cuda","fits","F16",8192,3.17,129536,false,169.4,null,null],["nvidia-geforce-rtx-4060","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,129536,false,169.4,null,null],["nvidia-geforce-rtx-4060","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,129536,false,169.4,null,null],["nvidia-geforce-rtx-4060","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"6",null],["nvidia-geforce-rtx-4060","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,111104,false,294.5,null,null],["nvidia-geforce-rtx-4060","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,111104,false,294.5,null,null],["nvidia-geforce-rtx-4060","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,111104,false,294.5,null,null],["nvidia-geforce-rtx-4060","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,28672,false,99.2,null,null],["nvidia-geforce-rtx-4060","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,40704,false,123.7,null,null],["nvidia-geforce-rtx-4060","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-4060","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-4060","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-4060","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-4060","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-4060","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,81.5,null,null],["nvidia-geforce-rtx-4060","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,11008,false,81.5,null,null],["nvidia-geforce-rtx-4060","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-4060","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-4060","mistral-7b-instruct-v0-2","cuda","fits","IQ2_M",8192,4.73,9216,false,77.3,null,null],["nvidia-geforce-rtx-4060","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4060","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-4060","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-4060","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-4060","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4060","nemotron-3-content-safety","cuda","fits","Q4_K_M",8192,4.69,16640,false,98.1,null,null],["nvidia-geforce-rtx-4060","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"8",null],["nvidia-geforce-rtx-4060","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-4060","nemotron-cascade-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","nemotron-cascade-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","nemotron-orchestrator-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-4060","nemotron-terminal-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-4060","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"7",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"7",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"6",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q5_K_M",8192,4.53,27136,false,91.3,null,null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"6",null],["nvidia-geforce-rtx-4060","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-4060","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-4060","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-4060","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-4060","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"5",null],["nvidia-geforce-rtx-4060","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-4060","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"4",null],["nvidia-geforce-rtx-4060","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-4060","olmocr-2-7b-1025","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-4060","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-4060","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-4060","phi-4-mini-instruct","cuda","fits","Q3_K_M",8192,4.54,10752,false,85.5,null,null],["nvidia-geforce-rtx-4060","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-4060","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,9216,false,75.9,null,null],["nvidia-geforce-rtx-4060","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen2-5-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,82.4,null,null],["nvidia-geforce-rtx-4060","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"5",null],["nvidia-geforce-rtx-4060","qwen2-5-coder-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,82.4,null,null],["nvidia-geforce-rtx-4060","qwen2-5-vl-7b-instruct","cuda","fits","Q2_K",8192,4.56,13568,false,82.4,null,null],["nvidia-geforce-rtx-4060","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q2_K",8192,4.56,13568,false,82.4,null,null],["nvidia-geforce-rtx-4060","qwen3-0-6b","cuda","fits","BF16",8192,3.41,20736,false,127.6,null,null],["nvidia-geforce-rtx-4060","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-4060","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"7",null],["nvidia-geforce-rtx-4060","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-4060","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"7",null],["nvidia-geforce-rtx-4060","qwen3-4b","cuda","tight","Q8_0",8192,6.7,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-4b-instruct-2507","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,129536,false,169.3,null,null],["nvidia-geforce-rtx-4060","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,191232,false,378.1,null,null],["nvidia-geforce-rtx-4060","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"6",null],["nvidia-geforce-rtx-4060","qwen3-5-2b","cuda","fits","Q8_0",8192,3.65,94976,false,129.4,null,null],["nvidia-geforce-rtx-4060","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,126720,false,165.2,null,null],["nvidia-geforce-rtx-4060","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-4060","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-4060","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-5-4b","cuda","fits","Q4_K_M",8192,4.66,14336,false,90.7,null,null],["nvidia-geforce-rtx-4060","qwen3-5-4b-base","cuda","fits","Q4_K_M",8192,4.63,15360,false,91.7,null,null],["nvidia-geforce-rtx-4060","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-5-9b-base","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"6",null],["nvidia-geforce-rtx-4060","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"4",null],["nvidia-geforce-rtx-4060","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-4060","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"8",null],["nvidia-geforce-rtx-4060","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-4060","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-4060","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-4060","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"5",null],["nvidia-geforce-rtx-4060","qwen3-vl-4b-instruct","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","qwen3-vl-4b-thinking","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"7",null],["nvidia-geforce-rtx-4060","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_0",8192,4.81,8192,false,75.5,null,null],["nvidia-geforce-rtx-4060","rlvr-8b-0926","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-4060","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-4060","singguard-2b","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","smollm3-3b","cuda","fits","Q6_K",8192,4.35,15104,false,87,null,null],["nvidia-geforce-rtx-4060","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,15104,false,87,null,null],["nvidia-geforce-rtx-4060","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","spatial-ssrl-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","spatial-ssrl-qwen3vl-4b","cuda","fits","IQ4_XS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-4060","step3-vl-10b-base","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,16384,false,108.4,null,null],["nvidia-geforce-rtx-4060","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,16384,false,108.4,null,null],["nvidia-geforce-rtx-4060","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,16384,false,108.4,null,null],["nvidia-geforce-rtx-4060","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,16384,false,108.4,null,null],["nvidia-geforce-rtx-4060","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-4060","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"5",null],["nvidia-geforce-rtx-4060","translategemma-4b-it","cuda","fits","Q4_K_M",8192,4.69,16640,false,98.1,null,null],["nvidia-geforce-rtx-4060","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-4060","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-4060","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-4060","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-4060","trinity-nano-base","cuda","fits","Q3_K_M",8192,4.74,14848,false,392.9,null,null],["nvidia-geforce-rtx-4060","trinity-nano-base-pre-anneal","cuda","fits","IQ4_XS",4096,4.81,4096,false,406.7,null,null],["nvidia-geforce-rtx-4060","trinity-nano-preview","cuda","fits","Q3_K_M",8192,4.65,20736,false,379.1,null,null],["nvidia-geforce-rtx-4060","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"4",null],["nvidia-geforce-rtx-4060","ui-mate-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-4060","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"5",null],["nvidia-geforce-rtx-4060","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"4",null],["nvidia-geforce-rtx-4060","ui-venus-1-5-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060","ui-venus-2-9b","cuda","tight","Q8_0",8192,10.27,null,null,null,null,null],["nvidia-geforce-rtx-4060","userrepgen-4b","cuda","fits","Q4_K_M",8192,4.65,14592,false,91.1,null,null],["nvidia-geforce-rtx-4060","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-4060","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"4",null],["nvidia-geforce-rtx-4060","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-4060","x-reasoner-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,52992,false,141.7,null,null],["nvidia-geforce-rtx-4060","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,52992,false,141.7,null,null],["nvidia-geforce-rtx-4060","youtu-vl-4b-instruct","cuda","fits","Q4_0",8192,4.85,8704,false,81.8,null,null],["nvidia-geforce-rtx-4060","zwz-2b","cuda","fits","Q8_0",8192,4.04,15360,false,98.3,null,null],["nvidia-geforce-rtx-4060","zwz-4b","cuda","fits","Q4_0",8192,4.83,8448,false,76,null,null],["nvidia-geforce-rtx-4060","zwz-7b","cuda","fits","IQ3_XXS",8192,4.6,12800,false,81.3,null,null],["nvidia-geforce-rtx-4060","zwz-8b","cuda","fits","IQ2_XXS",8192,4.74,8960,false,78,null,null],["nvidia-geforce-rtx-4060-ti-16gb","aescode-32b","cuda","fits","IQ2_XXS",8192,13.6,9216,false,23,null,null],["nvidia-geforce-rtx-4060-ti-16gb","aescode-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,63488,false,63.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,47.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,47.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ai21-jamba2-mini","cuda","fits","IQ2_XXS",8192,13.63,21760,false,85.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,110,null,null],["nvidia-geforce-rtx-4060-ti-16gb","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,110,null,null],["nvidia-geforce-rtx-4060-ti-16gb","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,89.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,15360,false,25.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","aprielguard","cuda","fits","Q6_K",8192,7.87,69120,false,42.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","armorocr","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","astabrief-8b","cuda","fits","Q6_K",8192,8.59,40960,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,65536,false,29.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,35.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,18176,false,26.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,30464,false,31.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,93.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,15616,false,24.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,40960,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","contextpilot-e4b","cuda","fits","F16",8192,10.89,131072,false,30.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,15360,false,26.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,44032,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,52.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,36608,false,31.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,14336,false,24.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","devstral-small-2-24b-instruct-2512","cuda","fits","Q3_K_M",8192,13.55,9984,false,23,null,null],["nvidia-geforce-rtx-4060-ti-16gb","eurollm-22b-2512","cuda","fits","Q3_K_M",8192,13.62,9216,false,22.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","eurollm-22b-instruct-2512","cuda","fits","Q3_K_M",8192,13.62,9216,false,22.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,20992,false,27.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,468.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","fara-7b","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","fara1-5-27b","cuda","fits","Q2_K",8192,13.61,12032,false,24.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","fara1-5-4b","cuda","fits","BF16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,113664,false,33,null,null],["nvidia-geforce-rtx-4060-ti-16gb","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,15360,false,26.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","frognano-4b-2609","cuda","fits","BF16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,505.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-2-27b-it","cuda","fits","IQ2_M",8192,13.78,8192,false,24.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,29,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-3-12b-it","cuda","fits","Q6_K",8192,13.02,20992,false,27.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,140.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,35.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,70656,false,28.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-26b-a4b","cuda","fits","Q2_K",8192,13,47616,false,128.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-26b-a4b-it","cuda","fits","Q2_K",8192,13.36,31232,false,110.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,147,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,61.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-e4b","cuda","fits","F16",8192,11,131072,false,30.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","gemma-4-e4b-it","cuda","fits","BF16",8192,11,131072,false,30.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,81152,false,29.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,28160,false,128.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,29952,false,115.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","gpt-oss-20b","cuda","fits","Q8_0",8192,12.9,45312,false,103.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,25088,false,28.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-0-1b","cuda","fits","BF16",8192,5.14,114176,false,73.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,306.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,96.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,402.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-1-3b","cuda","fits","BF16",8192,8.61,71936,false,38.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,23808,false,28.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-2-3b","cuda","fits","BF16",8192,8.61,71936,false,38.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,23808,false,28.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,25088,false,28.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,119808,false,83.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,23808,false,28.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,71936,false,38.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,50176,false,39.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,45.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","hermes-4-3-36b","cuda","fits","IQ2_XXS",8192,12.89,11776,false,24.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,122.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,400.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo-3-1-4b","cuda","fits","F16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,114176,false,33.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","holo2-30b-a3b","cuda","fits","Q2_K",8192,13.04,16640,false,136,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo2-4b","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo2-8b","cuda","fits","Q6_K",8192,8.59,44032,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo4-27b","cuda","fits","IQ3_XXS",8192,13.08,20224,false,25.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,93952,false,168,null,null],["nvidia-geforce-rtx-4060-ti-16gb","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,152.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"7",null],["nvidia-geforce-rtx-4060-ti-16gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,36608,false,31.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,36608,false,31.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,36608,false,31.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,36608,false,31.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","ising-calibration-1-35b-a3b","cuda","fits","IQ2_M",8192,13.14,41216,false,189.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","januscoder-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,78.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,38.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","kat-coder-v2-5-dev","cuda","fits","IQ2_M",8192,13.54,23040,false,164.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-linear-48b-a3b-instruct","cuda","fits","IQ2_XXS",8192,13.35,61184,false,214.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,115712,false,216.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","laguna-xs-2-1","cuda","fits","Q2_K",8192,13.77,10496,false,144,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,54.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,54.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,54.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,52.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,122.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,514.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,355.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,151.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,735.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,118,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,52.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,355.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,355.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,163.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,54.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,50176,false,39.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,105.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,55040,false,39.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","mathform-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,35.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,119808,false,137,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,119808,false,137,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,113152,false,130.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,119808,false,137,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,113152,false,130.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,119808,false,137,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,47104,false,41.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,113664,false,33,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,179.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,179.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,179.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,311.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,311.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,311.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,59.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,244480,false,131,null,null],["nvidia-geforce-rtx-4060-ti-16gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,22272,false,27.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,22272,false,27.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,55296,false,37.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,55296,false,37.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,31232,false,30,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,31232,false,30,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,41.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,20224,false,26.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q3_K_M",8192,13.55,9984,false,23,null,null],["nvidia-geforce-rtx-4060-ti-16gb","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,90880,false,25.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,82.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,15360,false,26.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,40960,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","north-mini-code-1-0","cuda","fits","Q2_K",8192,13.23,14336,false,129.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,262144,false,39.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,32.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,15872,false,29,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,10240,false,28.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,15872,false,29,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,15872,false,29,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,15872,false,29,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,10240,false,28.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,10240,false,28.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,13568,false,34.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","optimind-sft","cuda","fits","Q4_0",8192,13.22,33024,false,113.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,22528,false,40.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","phi-4","cuda","fits","Q5_K_M",8192,12.78,13568,false,24.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,37888,false,32.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,14336,false,24.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,80.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,89344,false,36.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,135.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-30b-a3b-instruct-2507","cuda","fits","Q2_K",8192,13.04,16640,false,136,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,52.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,179.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,400.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,74.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,175,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-35b-a3b-base","cuda","fits","IQ2_M",8192,13.02,46592,false,206.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-4b","cuda","fits","BF16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,114176,false,33.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,114176,false,33.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-6-35b-a3b","cuda","fits","IQ2_M",8192,13.54,23040,false,164.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-8-27b","cuda","fits","IQ3_XXS",8192,13.79,9472,false,24.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-8-3-6-27b-blend","cuda","fits","IQ3_XXS",8192,13.79,9472,false,24.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-30b-a3b-instruct","cuda","fits","Q2_K",8192,13.04,16640,false,136,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-reap-25b-a3b","cuda","fits","Q3_K_M",8192,13.26,14336,false,117.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,40960,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-30b-a3b-instruct","cuda","fits","Q2_K",8192,13.04,16640,false,136,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-4060-ti-16gb","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,60.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,44032,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,30208,false,29.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,15360,false,26.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","singguard-2b","cuda","fits","F16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,42.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,92.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,118016,false,45.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-4060-ti-16gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-4060-ti-16gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"7",null],["nvidia-geforce-rtx-4060-ti-16gb","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,40960,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","tiny-aya-earth","cuda","fits","BF16",8192,8.72,240640,false,40.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","tiny-aya-fire","cuda","fits","BF16",8192,8.72,240640,false,40.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","tiny-aya-global","cuda","fits","BF16",8192,8.72,240640,false,40.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","tiny-aya-water","cuda","fits","BF16",8192,8.72,240640,false,40.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","translategemma-12b-it","cuda","fits","Q6_K",8192,13.02,20992,false,27.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4060-ti-16gb","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,35.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-mini","cuda","fits","Q3_K_M",8192,13.65,19200,false,147.3,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,123648,false,184.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-mini-base-pre-anneal","cuda","fits","Q3_K_M",4096,13.8,4096,false,160.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,319.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,342.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","trinity-nano-preview","cuda","fits","BF16",8192,13.51,29440,false,155,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-mate-27b","cuda","fits","Q2_K",8192,13.61,12032,false,24.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,113664,false,33,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,25344,false,26.6,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-venus-1-5-30b-a3b","cuda","fits","Q2_K",8192,13.04,16640,false,136,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,44032,false,38.8,null,null],["nvidia-geforce-rtx-4060-ti-16gb","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,113664,false,33,null,null],["nvidia-geforce-rtx-4060-ti-16gb","userrepgen-4b","cuda","fits","BF16",8192,10.23,114688,false,33.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,17152,false,25.5,null,null],["nvidia-geforce-rtx-4060-ti-16gb","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,15360,false,26.4,null,null],["nvidia-geforce-rtx-4060-ti-16gb","webworld-8b","cuda","fits","Q8_0",8192,10.39,31744,false,31.1,null,null],["nvidia-geforce-rtx-4060-ti-16gb","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,118016,false,45.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,150,null,null],["nvidia-geforce-rtx-4060-ti-16gb","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,150,null,null],["nvidia-geforce-rtx-4060-ti-16gb","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,65.2,null,null],["nvidia-geforce-rtx-4060-ti-16gb","zwz-2b","cuda","fits","F16",8192,5.62,80128,false,65.7,null,null],["nvidia-geforce-rtx-4060-ti-16gb","zwz-4b","cuda","fits","Q6_K",8192,5.74,63488,false,63.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","zwz-7b","cuda","fits","Q6_K",8192,7.47,118016,false,45.9,null,null],["nvidia-geforce-rtx-4060-ti-16gb","zwz-8b","cuda","fits","Q6_K",8192,8.59,44032,false,38.8,null,null],["nvidia-geforce-rtx-4070","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-rtx-4070","aescode-8b","cuda","fits","Q5_K_M",8192,8.2,12544,false,71.8,null,null],["nvidia-geforce-rtx-4070","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,29440,false,111.8,null,null],["nvidia-geforce-rtx-4070","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,83,null,null],["nvidia-geforce-rtx-4070","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,83,null,null],["nvidia-geforce-rtx-4070","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-rtx-4070","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,192.5,null,null],["nvidia-geforce-rtx-4070","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,192.5,null,null],["nvidia-geforce-rtx-4070","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,157,null,null],["nvidia-geforce-rtx-4070","apriel-1-6-15b-thinker","cuda","fits","IQ3_XXS",8192,8.24,11264,false,71,null,null],["nvidia-geforce-rtx-4070","aprielguard","cuda","fits","Q6_K",8192,7.87,18176,false,75,null,null],["nvidia-geforce-rtx-4070","armorocr","cuda","fits","Q4_K_M",8192,7.09,20224,false,85.7,null,null],["nvidia-geforce-rtx-4070","astabrief-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","autoglm-phone-9b","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070","autoglm-phone-9b-multilingual","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4070","bielik-11b-v3-0-instruct","cuda","tight","Q8_0",8192,14.42,null,null,null,null,null],["nvidia-geforce-rtx-4070","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q6_K",8192,8.5,10240,false,68.4,null,null],["nvidia-geforce-rtx-4070","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,164,null,null],["nvidia-geforce-rtx-4070","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4070","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","contextpilot-14b","cuda","fits","IQ3_XXS",8192,8.43,10752,false,69.5,null,null],["nvidia-geforce-rtx-4070","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,131072,false,98.5,null,null],["nvidia-geforce-rtx-4070","cosmos-reason2-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,91.2,null,null],["nvidia-geforce-rtx-4070","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4070","deepseek-r1-0528-qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-4070","deepseek-r1-distill-llama-8b","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","deepseek-r1-distill-qwen-14b","cuda","fits","Q2_K",8192,8.3,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4070","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4070","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4070","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-4070","devstral-small-2-24b-instruct-2512","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070","eurollm-22b-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-4070","eurollm-22b-instruct-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-4070","eurollm-9b-instruct-2512","cuda","fits","Q5_K_M",8192,8.69,9216,false,66.6,null,null],["nvidia-geforce-rtx-4070","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,819.9,null,null],["nvidia-geforce-rtx-4070","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"3",null],["nvidia-geforce-rtx-4070","fara-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","fara1-5-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-4070","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070","fara1-5-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070","frogboss-32b-2510","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070","frogmini-14b-2510","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,885.2,null,null],["nvidia-geforce-rtx-4070","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","gemma-2-27b-it","cuda","tight","IQ3_XXS",8192,15.11,null,null,null,null,null],["nvidia-geforce-rtx-4070","gemma-2-9b-it","cuda","fits","IQ3_XXS",8192,8.03,8192,false,85.4,null,null],["nvidia-geforce-rtx-4070","gemma-3-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,89.5,null,null],["nvidia-geforce-rtx-4070","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,246.4,null,null],["nvidia-geforce-rtx-4070","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-4070","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-4070","gemma-4-12b-it","cuda","fits","Q3_K_M",8192,8.73,16128,false,82,null,null],["nvidia-geforce-rtx-4070","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-4070","gemma-4-26b-a4b-it","cuda","tight","Q3_K_M",8192,15.39,null,null,null,null,null],["nvidia-geforce-rtx-4070","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-rtx-4070","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"3",null],["nvidia-geforce-rtx-4070","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,257.2,null,null],["nvidia-geforce-rtx-4070","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,108.3,null,null],["nvidia-geforce-rtx-4070","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,128256,false,97.4,null,null],["nvidia-geforce-rtx-4070","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,119296,false,94.4,null,null],["nvidia-geforce-rtx-4070","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-4070","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-rtx-4070","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-4070","glm-4-6v-flash","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-rtx-4070","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q4_0",8192,14.61,null,null,null,null,null],["nvidia-geforce-rtx-4070","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4070","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-rtx-4070","granite-3-3-8b-instruct","cuda","fits","Q5_K_M",8192,8.28,11776,false,70.6,null,null],["nvidia-geforce-rtx-4070","granite-4-0-1b","cuda","fits","BF16",8192,5.14,53504,false,128.1,null,null],["nvidia-geforce-rtx-4070","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,536.3,null,null],["nvidia-geforce-rtx-4070","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,168.5,null,null],["nvidia-geforce-rtx-4070","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,705,null,null],["nvidia-geforce-rtx-4070","granite-4-1-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070","granite-4-1-3b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070","granite-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070","granite-4-2-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070","granite-4-2-3b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070","granite-4-2-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q5_K_M",8192,8.28,11776,false,70.6,null,null],["nvidia-geforce-rtx-4070","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,59136,false,145.5,null,null],["nvidia-geforce-rtx-4070","granite-guardian-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-rtx-4070","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,214.3,null,null],["nvidia-geforce-rtx-4070","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,700.5,null,null],["nvidia-geforce-rtx-4070","holo-3-1-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-4070","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070","holo-3-1-9b","cuda","fits","Q6_K",8192,8.37,22784,false,74.3,null,null],["nvidia-geforce-rtx-4070","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070","holo2-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","holo2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","holo3-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-4070","holo4-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-4070","holo4-35b-a3b","cuda","tight","Q2_K",8192,14.96,null,null,null,null,null],["nvidia-geforce-rtx-4070","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,267.6,null,null],["nvidia-geforce-rtx-4070","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-4070","ising-calibration-1-35b-a3b","cuda","tight","IQ3_XXS",8192,15.07,null,null,null,null,null],["nvidia-geforce-rtx-4070","ising-calibration-1-5-31b-bf16","cuda","tight","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-rtx-4070","januscoder-14b","cuda","fits","Q2_K",8192,8.02,13312,false,73.7,null,null],["nvidia-geforce-rtx-4070","januscoder-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-4070","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,136.8,null,null],["nvidia-geforce-rtx-4070","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,10496,false,67.8,null,null],["nvidia-geforce-rtx-4070","kat-coder-v2-5-dev","cuda","tight","Q2_K",8192,14.13,null,null,null,null,null],["nvidia-geforce-rtx-4070","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"4",null],["nvidia-geforce-rtx-4070","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4070","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4070","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4070","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4070","kimi-linear-48b-a3b-base","cuda","tight","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-rtx-4070","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-rtx-4070","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ3_XXS",8192,14.77,null,null,null,null,null],["nvidia-geforce-rtx-4070","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-rtx-4070","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070","lfm2-24b-a2b","cuda","tight","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-rtx-4070","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,128256,false,91.2,null,null],["nvidia-geforce-rtx-4070","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,214.7,null,null],["nvidia-geforce-rtx-4070","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,899.7,null,null],["nvidia-geforce-rtx-4070","lfm2-5-24b-a2b","cuda","tight","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-8b-a1b","cuda","fits","Q6_K",8192,8.19,56576,false,338.6,null,null],["nvidia-geforce-rtx-4070","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1286.8,null,null],["nvidia-geforce-rtx-4070","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,91.2,null,null],["nvidia-geforce-rtx-4070","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070","lfm2-8b-a1b","cuda","fits","Q6_K",8192,8.09,63744,false,364.2,null,null],["nvidia-geforce-rtx-4070","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"3",null],["nvidia-geforce-rtx-4070","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,183.9,null,null],["nvidia-geforce-rtx-4070","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,11264,false,68.4,null,null],["nvidia-geforce-rtx-4070","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-4070","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"6",null],["nvidia-geforce-rtx-4070","mathform-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q8_0",8192,14.03,null,null,null,null,null],["nvidia-geforce-rtx-4070","mellum2-12b-a2-5b-base","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070","mellum2-12b-a2-5b-instruct","cuda","fits","Q4_0",8192,8.34,41728,false,325.3,null,null],["nvidia-geforce-rtx-4070","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070","mellum2-12b-a2-5b-thinking","cuda","fits","Q4_0",8192,8.34,41728,false,325.3,null,null],["nvidia-geforce-rtx-4070","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,13056,false,72.5,null,null],["nvidia-geforce-rtx-4070","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mimo-v2-6-distill-qwen-9b","cuda","fits","Q6_K",8192,8.8,10240,false,69.8,null,null],["nvidia-geforce-rtx-4070","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-4070","minicpm-o-4-5","cuda","fits","Q6_K",8192,8.59,9984,false,68,null,null],["nvidia-geforce-rtx-4070","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-rtx-4070","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070","minicpm5-2b","cuda","fits","BF16",8192,6.04,72448,false,103.9,null,null],["nvidia-geforce-rtx-4070","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,131328,false,229.3,null,null],["nvidia-geforce-rtx-4070","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"6",null],["nvidia-geforce-rtx-4070","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-4070","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-4070","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,8192,false,65.2,null,null],["nvidia-geforce-rtx-4070","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,8192,false,65.2,null,null],["nvidia-geforce-rtx-4070","ministral-3-8b-instruct-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,73.9,null,null],["nvidia-geforce-rtx-4070","ministral-3-8b-reasoning-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,73.9,null,null],["nvidia-geforce-rtx-4070","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,14336,false,73,null,null],["nvidia-geforce-rtx-4070","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4070","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-4070","mistral-nemo-instruct-2407","cuda","fits","IQ4_XS",8192,8.85,8192,false,65.3,null,null],["nvidia-geforce-rtx-4070","mistral-small-3-2-24b-instruct-2506","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"7",null],["nvidia-geforce-rtx-4070","muse-glimmer-30b","cuda","tight","Q3_K_M",8192,14.97,null,null,null,null,null],["nvidia-geforce-rtx-4070","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4070","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,145.1,null,null],["nvidia-geforce-rtx-4070","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-rtx-4070","nemotron-cascade-14b-thinking","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-4070","nemotron-cascade-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","nemotron-cascade-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","nemotron-orchestrator-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","nemotron-terminal-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","nemotron-terminal-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","north-mini-code-1-0","cuda","tight","IQ3_XXS",8192,15.09,null,null,null,null,null],["nvidia-geforce-rtx-4070","nouscoder-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,15872,false,69.4,null,null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"7",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"7",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070","nvidia-nemotron-nano-9b-v2","cuda","fits","Q5_K_M",8192,8.47,30208,false,74.6,null,null],["nvidia-geforce-rtx-4070","olmo-3-1-32b-instruct","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-1-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-1-7b-rl-zero-math","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070","olmo-3-1125-32b","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-32b-think-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-32b-think-sft","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-instruct","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-instruct-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-instruct-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-rl-zero-general","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-rl-zero-if","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-rl-zero-math","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-rl-zero-mix","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-think","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-think-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmo-3-7b-think-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-rtx-4070","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,9472,false,70.2,null,null],["nvidia-geforce-rtx-4070","phi-4","cuda","fits","Q2_K",8192,8.25,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,26624,false,97.9,null,null],["nvidia-geforce-rtx-4070","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-rtx-4070","qwen2-5-14b-instruct","cuda","fits","Q2_K",8192,8.3,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,140.7,null,null],["nvidia-geforce-rtx-4070","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-rtx-4070","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,236.4,null,null],["nvidia-geforce-rtx-4070","qwen3-1-7b","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","qwen3-14b","cuda","tight","Q6_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-4070","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"3",null],["nvidia-geforce-rtx-4070","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"3",null],["nvidia-geforce-rtx-4070","qwen3-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,313.7,null,null],["nvidia-geforce-rtx-4070","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,700.5,null,null],["nvidia-geforce-rtx-4070","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-rtx-4070","qwen3-5-27b","cuda","tight","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-5-2b","cuda","fits","BF16",8192,5.38,256512,false,130.4,null,null],["nvidia-geforce-rtx-4070","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,306.2,null,null],["nvidia-geforce-rtx-4070","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-4070","qwen3-5-35b-a3b-base","cuda","tight","IQ3_XXS",8192,14.98,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070","qwen3-5-9b","cuda","fits","Q6_K",8192,8.47,19968,false,73.2,null,null],["nvidia-geforce-rtx-4070","qwen3-5-9b-base","cuda","fits","Q6_K",8192,8.37,22784,false,74.3,null,null],["nvidia-geforce-rtx-4070","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"2",null],["nvidia-geforce-rtx-4070","qwen3-6-35b-a3b","cuda","tight","Q2_K",8192,14.12,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4070","qwen3-8-27b","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-8-3-6-27b-blend","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4070","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-rtx-4070","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"3",null],["nvidia-geforce-rtx-4070","qwen3-coder-reap-25b-a3b","cuda","fits","IQ2_XXS",8192,8.11,15872,false,269.1,null,null],["nvidia-geforce-rtx-4070","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-4070","qwen3-nemotron-14b-brrm","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-rtx-4070","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-4070","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-4070","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-8b-instruct","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","qwen3-vl-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"3",null],["nvidia-geforce-rtx-4070","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,105.2,null,null],["nvidia-geforce-rtx-4070","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","rnj-1-instruct","cuda","fits","Q5_K_M",8192,8.15,13568,false,71.9,null,null],["nvidia-geforce-rtx-4070","sera-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070","singguard-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","smollm3-3b","cuda","fits","BF16",8192,7.9,21248,false,74.6,null,null],["nvidia-geforce-rtx-4070","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,161.2,null,null],["nvidia-geforce-rtx-4070","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-rtx-4070","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8",null],["nvidia-geforce-rtx-4070","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"5",null],["nvidia-geforce-rtx-4070","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"6",null],["nvidia-geforce-rtx-4070","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","tiny-aya-earth","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070","tiny-aya-fire","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070","tiny-aya-global","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070","tiny-aya-water","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070","translategemma-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,89.5,null,null],["nvidia-geforce-rtx-4070","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-4070","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070","trinity-mini","cuda","fits","IQ2_XXS",8192,8.25,41216,false,366.5,null,null],["nvidia-geforce-rtx-4070","trinity-mini-base","cuda","fits","IQ2_XXS",8192,8.69,16640,false,404.8,null,null],["nvidia-geforce-rtx-4070","trinity-mini-base-pre-anneal","cuda","fits","IQ2_XXS",4096,8.41,4096,false,427.9,null,null],["nvidia-geforce-rtx-4070","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,559.6,null,null],["nvidia-geforce-rtx-4070","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,598.7,null,null],["nvidia-geforce-rtx-4070","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,56320,false,459.4,null,null],["nvidia-geforce-rtx-4070","ui-mate-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-4070","ui-mate-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070","ui-mate-democua-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-4070","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","ui-venus-2-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070","webworld-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070","webworld-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070","webworld-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,262.5,null,null],["nvidia-geforce-rtx-4070","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,262.5,null,null],["nvidia-geforce-rtx-4070","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,114.2,null,null],["nvidia-geforce-rtx-4070","zwz-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070","zwz-4b","cuda","fits","Q6_K",8192,5.74,29440,false,111.8,null,null],["nvidia-geforce-rtx-4070","zwz-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070","zwz-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","aescode-8b","cuda","fits","Q5_K_M",8192,8.2,12544,false,71.8,null,null],["nvidia-geforce-rtx-4070-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,29440,false,111.8,null,null],["nvidia-geforce-rtx-4070-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,83,null,null],["nvidia-geforce-rtx-4070-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,83,null,null],["nvidia-geforce-rtx-4070-ti","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,192.5,null,null],["nvidia-geforce-rtx-4070-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,192.5,null,null],["nvidia-geforce-rtx-4070-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,157,null,null],["nvidia-geforce-rtx-4070-ti","apriel-1-6-15b-thinker","cuda","fits","IQ3_XXS",8192,8.24,11264,false,71,null,null],["nvidia-geforce-rtx-4070-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,18176,false,75,null,null],["nvidia-geforce-rtx-4070-ti","armorocr","cuda","fits","Q4_K_M",8192,7.09,20224,false,85.7,null,null],["nvidia-geforce-rtx-4070-ti","astabrief-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","autoglm-phone-9b","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070-ti","autoglm-phone-9b-multilingual","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","bielik-11b-v3-0-instruct","cuda","tight","Q8_0",8192,14.42,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q6_K",8192,8.5,10240,false,68.4,null,null],["nvidia-geforce-rtx-4070-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,164,null,null],["nvidia-geforce-rtx-4070-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","contextpilot-14b","cuda","fits","IQ3_XXS",8192,8.43,10752,false,69.5,null,null],["nvidia-geforce-rtx-4070-ti","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,131072,false,98.5,null,null],["nvidia-geforce-rtx-4070-ti","cosmos-reason2-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,91.2,null,null],["nvidia-geforce-rtx-4070-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-distill-llama-8b","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-distill-qwen-14b","cuda","fits","Q2_K",8192,8.3,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","devstral-small-2-24b-instruct-2512","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","eurollm-22b-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","eurollm-22b-instruct-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","eurollm-9b-instruct-2512","cuda","fits","Q5_K_M",8192,8.69,9216,false,66.6,null,null],["nvidia-geforce-rtx-4070-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,819.9,null,null],["nvidia-geforce-rtx-4070-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","fara-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","fara1-5-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070-ti","fara1-5-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","frogboss-32b-2510","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","frogmini-14b-2510","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,885.2,null,null],["nvidia-geforce-rtx-4070-ti","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","gemma-2-27b-it","cuda","tight","IQ3_XXS",8192,15.11,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","gemma-2-9b-it","cuda","fits","IQ3_XXS",8192,8.03,8192,false,85.4,null,null],["nvidia-geforce-rtx-4070-ti","gemma-3-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,89.5,null,null],["nvidia-geforce-rtx-4070-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,246.4,null,null],["nvidia-geforce-rtx-4070-ti","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-12b-it","cuda","fits","Q3_K_M",8192,8.73,16128,false,82,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-26b-a4b-it","cuda","tight","Q3_K_M",8192,15.39,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,257.2,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,108.3,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,128256,false,97.4,null,null],["nvidia-geforce-rtx-4070-ti","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,119296,false,94.4,null,null],["nvidia-geforce-rtx-4070-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","glm-4-6v-flash","cuda","fits","Q5_K_M",8192,8.13,25600,false,72.5,null,null],["nvidia-geforce-rtx-4070-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q4_0",8192,14.61,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","granite-3-3-8b-instruct","cuda","fits","Q5_K_M",8192,8.28,11776,false,70.6,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,53504,false,128.1,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,536.3,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,168.5,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,705,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-1-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-1-3b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-2-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-2-3b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070-ti","granite-4-2-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q5_K_M",8192,8.28,11776,false,70.6,null,null],["nvidia-geforce-rtx-4070-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,59136,false,145.5,null,null],["nvidia-geforce-rtx-4070-ti","granite-guardian-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,68.9,null,null],["nvidia-geforce-rtx-4070-ti","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,11264,false,67.4,null,null],["nvidia-geforce-rtx-4070-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,214.3,null,null],["nvidia-geforce-rtx-4070-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,700.5,null,null],["nvidia-geforce-rtx-4070-ti","holo-3-1-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070-ti","holo-3-1-9b","cuda","fits","Q6_K",8192,8.37,22784,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","holo2-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","holo2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","holo3-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","holo4-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","holo4-35b-a3b","cuda","tight","Q2_K",8192,14.96,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,267.6,null,null],["nvidia-geforce-rtx-4070-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","ising-calibration-1-35b-a3b","cuda","tight","IQ3_XXS",8192,15.07,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ising-calibration-1-5-31b-bf16","cuda","tight","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","januscoder-14b","cuda","fits","Q2_K",8192,8.02,13312,false,73.7,null,null],["nvidia-geforce-rtx-4070-ti","januscoder-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,136.8,null,null],["nvidia-geforce-rtx-4070-ti","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,10496,false,67.8,null,null],["nvidia-geforce-rtx-4070-ti","kat-coder-v2-5-dev","cuda","tight","Q2_K",8192,14.13,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","kimi-linear-48b-a3b-base","cuda","tight","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ3_XXS",8192,14.77,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-24b-a2b","cuda","tight","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,128256,false,91.2,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,214.7,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,899.7,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-24b-a2b","cuda","tight","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-8b-a1b","cuda","fits","Q6_K",8192,8.19,56576,false,338.6,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1286.8,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,206.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,91.2,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,622.4,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-8b-a1b","cuda","fits","Q6_K",8192,8.09,63744,false,364.2,null,null],["nvidia-geforce-rtx-4070-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,95.6,null,null],["nvidia-geforce-rtx-4070-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,69.7,null,null],["nvidia-geforce-rtx-4070-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,183.9,null,null],["nvidia-geforce-rtx-4070-ti","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,11264,false,68.4,null,null],["nvidia-geforce-rtx-4070-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","mathform-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q8_0",8192,14.03,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-12b-a2-5b-base","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q4_0",8192,8.34,41728,false,325.3,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q4_0",8192,8.34,41728,false,325.3,null,null],["nvidia-geforce-rtx-4070-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q4_0",8192,8.27,45824,false,340,null,null],["nvidia-geforce-rtx-4070-ti","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,13056,false,72.5,null,null],["nvidia-geforce-rtx-4070-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","Q6_K",8192,8.8,10240,false,69.8,null,null],["nvidia-geforce-rtx-4070-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","minicpm-o-4-5","cuda","fits","Q6_K",8192,8.59,9984,false,68,null,null],["nvidia-geforce-rtx-4070-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,313.8,null,null],["nvidia-geforce-rtx-4070-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,545.7,null,null],["nvidia-geforce-rtx-4070-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,72448,false,103.9,null,null],["nvidia-geforce-rtx-4070-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,131328,false,229.3,null,null],["nvidia-geforce-rtx-4070-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,8192,false,65.2,null,null],["nvidia-geforce-rtx-4070-ti","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,8192,false,65.2,null,null],["nvidia-geforce-rtx-4070-ti","ministral-3-8b-instruct-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,73.9,null,null],["nvidia-geforce-rtx-4070-ti","ministral-3-8b-reasoning-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,73.9,null,null],["nvidia-geforce-rtx-4070-ti","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,14336,false,73,null,null],["nvidia-geforce-rtx-4070-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","mistral-nemo-instruct-2407","cuda","fits","IQ4_XS",8192,8.85,8192,false,65.3,null,null],["nvidia-geforce-rtx-4070-ti","mistral-small-3-2-24b-instruct-2506","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","muse-glimmer-30b","cuda","tight","Q3_K_M",8192,14.97,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,145.1,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti","nemotron-cascade-14b-thinking","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","nemotron-cascade-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-cascade-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-orchestrator-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-terminal-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-terminal-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","north-mini-code-1-0","cuda","tight","IQ3_XXS",8192,15.09,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","nouscoder-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,15872,false,69.4,null,null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","Q5_K_M",8192,8.47,30208,false,74.6,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1-32b-instruct","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1-7b-rl-zero-math","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-1125-32b","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-32b-think-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-32b-think-sft","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-instruct","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-instruct-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-instruct-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-rl-zero-general","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-rl-zero-if","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-rl-zero-math","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-rl-zero-mix","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-think","cuda","fits","Q2_K",8192,8.17,9472,false,93.3,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-think-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmo-3-7b-think-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,93.2,null,null],["nvidia-geforce-rtx-4070-ti","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,9472,false,70.2,null,null],["nvidia-geforce-rtx-4070-ti","phi-4","cuda","fits","Q2_K",8192,8.25,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,26624,false,97.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","qwen2-5-14b-instruct","cuda","fits","Q2_K",8192,8.3,11008,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,140.7,null,null],["nvidia-geforce-rtx-4070-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,236.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-14b","cuda","tight","Q6_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,313.7,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,700.5,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","qwen3-5-27b","cuda","tight","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,256512,false,130.4,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,306.2,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","qwen3-5-35b-a3b-base","cuda","tight","IQ3_XXS",8192,14.98,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,81408,false,106.3,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-9b","cuda","fits","Q6_K",8192,8.47,19968,false,73.2,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-5-9b-base","cuda","fits","Q6_K",8192,8.37,22784,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","qwen3-6-35b-a3b","cuda","tight","Q2_K",8192,14.12,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","qwen3-8-27b","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-8-3-6-27b-blend","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-reap-25b-a3b","cuda","fits","IQ2_XXS",8192,8.11,15872,false,269.1,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti","qwen3-nemotron-14b-brrm","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-8b-instruct","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","qwen3-vl-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,105.2,null,null],["nvidia-geforce-rtx-4070-ti","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","rnj-1-instruct","cuda","fits","Q5_K_M",8192,8.15,13568,false,71.9,null,null],["nvidia-geforce-rtx-4070-ti","sera-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","singguard-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","smollm3-3b","cuda","fits","BF16",8192,7.9,21248,false,74.6,null,null],["nvidia-geforce-rtx-4070-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,161.2,null,null],["nvidia-geforce-rtx-4070-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,91.9,null,null],["nvidia-geforce-rtx-4070-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","tiny-aya-earth","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070-ti","tiny-aya-fire","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070-ti","tiny-aya-global","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070-ti","tiny-aya-water","cuda","fits","BF16",8192,8.72,10240,false,71.2,null,null],["nvidia-geforce-rtx-4070-ti","translategemma-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,89.5,null,null],["nvidia-geforce-rtx-4070-ti","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,114.2,null,null],["nvidia-geforce-rtx-4070-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti","trinity-mini","cuda","fits","IQ2_XXS",8192,8.25,41216,false,366.5,null,null],["nvidia-geforce-rtx-4070-ti","trinity-mini-base","cuda","fits","IQ2_XXS",8192,8.69,16640,false,404.8,null,null],["nvidia-geforce-rtx-4070-ti","trinity-mini-base-pre-anneal","cuda","fits","IQ2_XXS",4096,8.41,4096,false,427.9,null,null],["nvidia-geforce-rtx-4070-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,559.6,null,null],["nvidia-geforce-rtx-4070-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,598.7,null,null],["nvidia-geforce-rtx-4070-ti","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,56320,false,459.4,null,null],["nvidia-geforce-rtx-4070-ti","ui-mate-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ui-mate-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","ui-mate-democua-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","ui-venus-2-9b","cuda","fits","Q6_K",8192,8.7,13056,false,70.8,null,null],["nvidia-geforce-rtx-4070-ti","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,81152,false,106.1,null,null],["nvidia-geforce-rtx-4070-ti","webworld-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti","webworld-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti","webworld-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,262.5,null,null],["nvidia-geforce-rtx-4070-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,262.5,null,null],["nvidia-geforce-rtx-4070-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,114.2,null,null],["nvidia-geforce-rtx-4070-ti","zwz-2b","cuda","fits","F16",8192,5.62,36608,false,115,null,null],["nvidia-geforce-rtx-4070-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,29440,false,111.8,null,null],["nvidia-geforce-rtx-4070-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,32256,false,80.4,null,null],["nvidia-geforce-rtx-4070-ti","zwz-8b","cuda","fits","Q6_K",8192,8.59,9984,false,67.9,null,null],["nvidia-geforce-rtx-4070-ti-super","aescode-32b","cuda","tight","Q3_K_M",8192,19.28,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","aescode-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,56832,false,149.1,null,null],["nvidia-geforce-rtx-4070-ti-super","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,110.6,null,null],["nvidia-geforce-rtx-4070-ti-super","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,110.6,null,null],["nvidia-geforce-rtx-4070-ti-super","ai21-jamba2-mini","cuda","tight","Q2_K",8192,19.01,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,256.7,null,null],["nvidia-geforce-rtx-4070-ti-super","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,256.7,null,null],["nvidia-geforce-rtx-4070-ti-super","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,209.3,null,null],["nvidia-geforce-rtx-4070-ti-super","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,10240,false,58.9,null,null],["nvidia-geforce-rtx-4070-ti-super","aprielguard","cuda","fits","Q6_K",8192,7.87,58880,false,99.9,null,null],["nvidia-geforce-rtx-4070-ti-super","armorocr","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","astabrief-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,57344,false,69.5,null,null],["nvidia-geforce-rtx-4070-ti-super","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,83.1,null,null],["nvidia-geforce-rtx-4070-ti-super","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti-super","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,13312,false,62.6,null,null],["nvidia-geforce-rtx-4070-ti-super","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,24320,false,73.5,null,null],["nvidia-geforce-rtx-4070-ti-super","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,218.7,null,null],["nvidia-geforce-rtx-4070-ti-super","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti-super","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,9472,false,58.2,null,null],["nvidia-geforce-rtx-4070-ti-super","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","contextpilot-e4b","cuda","fits","F16",8192,10.89,118016,false,71.1,null,null],["nvidia-geforce-rtx-4070-ti-super","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,61.6,null,null],["nvidia-geforce-rtx-4070-ti-super","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,121.5,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,28928,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,9216,false,58,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","devstral-small-2-24b-instruct-2512","cuda","fits","Q2_K",8192,11.09,18944,false,67.2,null,null],["nvidia-geforce-rtx-4070-ti-super","eurollm-22b-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,64.4,null,null],["nvidia-geforce-rtx-4070-ti-super","eurollm-22b-instruct-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,64.4,null,null],["nvidia-geforce-rtx-4070-ti-super","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,15360,false,63.5,null,null],["nvidia-geforce-rtx-4070-ti-super","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1093.3,null,null],["nvidia-geforce-rtx-4070-ti-super","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","fara-7b","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","fara1-5-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,63.3,null,null],["nvidia-geforce-rtx-4070-ti-super","fara1-5-4b","cuda","fits","BF16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,84224,false,77,null,null],["nvidia-geforce-rtx-4070-ti-super","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,11264,false,61.6,null,null],["nvidia-geforce-rtx-4070-ti-super","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","frognano-4b-2609","cuda","fits","BF16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1180.3,null,null],["nvidia-geforce-rtx-4070-ti-super","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-2-27b-it","cuda","tight","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,67.7,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-3-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,72.2,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,328.6,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,83.5,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,15360,false,65.6,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-26b-a4b","cuda","tight","Q4_K_M",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-26b-a4b-it","cuda","fits","IQ2_XXS",8192,12.09,43520,false,293.4,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,343,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,144.4,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-e4b","cuda","fits","F16",8192,11,111872,false,70.3,null,null],["nvidia-geforce-rtx-4070-ti-super","gemma-4-e4b-it","cuda","fits","BF16",8192,11,111872,false,70.3,null,null],["nvidia-geforce-rtx-4070-ti-super","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,57344,false,69.5,null,null],["nvidia-geforce-rtx-4070-ti-super","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,9984,false,299.1,null,null],["nvidia-geforce-rtx-4070-ti-super","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,11776,false,268.7,null,null],["nvidia-geforce-rtx-4070-ti-super","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti-super","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti-super","gpt-oss-20b","cuda","fits","Q6_K",8192,12.83,9728,false,247.9,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,18944,false,67,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-0-1b","cuda","fits","BF16",8192,5.14,102144,false,170.8,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,715.1,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,224.6,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,940,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-1-3b","cuda","fits","BF16",8192,8.61,59904,false,89.9,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,65.6,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-2-3b","cuda","fits","BF16",8192,8.61,59904,false,89.9,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,17664,false,65.6,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,18944,false,67,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,107776,false,194,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,65.6,null,null],["nvidia-geforce-rtx-4070-ti-super","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,59904,false,89.9,null,null],["nvidia-geforce-rtx-4070-ti-super","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,92.9,null,null],["nvidia-geforce-rtx-4070-ti-super","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,107.2,null,null],["nvidia-geforce-rtx-4070-ti-super","hermes-4-3-36b","cuda","tight","IQ3_XXS",8192,16.93,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,285.8,null,null],["nvidia-geforce-rtx-4070-ti-super","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,934.1,null,null],["nvidia-geforce-rtx-4070-ti-super","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","holo-3-1-4b","cuda","fits","F16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,84736,false,77.2,null,null],["nvidia-geforce-rtx-4070-ti-super","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti-super","holo2-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","holo2-4b","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","holo2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","holo4-27b","cuda","fits","Q2_K",8192,12.74,10240,false,62.1,null,null],["nvidia-geforce-rtx-4070-ti-super","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,48640,false,392,null,null],["nvidia-geforce-rtx-4070-ti-super","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,356.8,null,null],["nvidia-geforce-rtx-4070-ti-super","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,28928,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,28928,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,28928,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,28928,false,74.3,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","ising-calibration-1-35b-a3b","cuda","fits","IQ2_XXS",8192,11.07,89600,false,484.3,null,null],["nvidia-geforce-rtx-4070-ti-super","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","januscoder-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,182.4,null,null],["nvidia-geforce-rtx-4070-ti-super","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,90.4,null,null],["nvidia-geforce-rtx-4070-ti-super","kat-coder-v2-5-dev","cuda","fits","IQ2_XXS",8192,11.35,77056,false,407.3,null,null],["nvidia-geforce-rtx-4070-ti-super","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","kimi-linear-48b-a3b-instruct","cuda","tight","Q2_K",8192,18.65,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,14848,false,505.5,null,null],["nvidia-geforce-rtx-4070-ti-super","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","laguna-xs-2-1","cuda","fits","IQ2_XXS",8192,11.07,50944,false,368.6,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,121.5,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,286.3,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1199.7,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,354.3,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1715.8,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,121.5,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,381.7,null,null],["nvidia-geforce-rtx-4070-ti-super","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-4070-ti-super","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,92.9,null,null],["nvidia-geforce-rtx-4070-ti-super","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,245.2,null,null],["nvidia-geforce-rtx-4070-ti-super","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,46336,false,91.2,null,null],["nvidia-geforce-rtx-4070-ti-super","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","mathform-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,83.5,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,57600,false,319.7,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,57600,false,319.7,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,50688,false,303.5,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,57600,false,319.7,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,50688,false,303.5,null,null],["nvidia-geforce-rtx-4070-ti-super","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,57600,false,319.7,null,null],["nvidia-geforce-rtx-4070-ti-super","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,40448,false,96.7,null,null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,84224,false,77,null,null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,25088,false,72.7,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,138.5,null,null],["nvidia-geforce-rtx-4070-ti-super","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,221696,false,305.7,null,null],["nvidia-geforce-rtx-4070-ti-super","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,64,null,null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,64,null,null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,45824,false,86.9,null,null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,45824,false,86.9,null,null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,23808,false,70.1,null,null],["nvidia-geforce-rtx-4070-ti-super","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,23808,false,70.1,null,null],["nvidia-geforce-rtx-4070-ti-super","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,97.3,null,null],["nvidia-geforce-rtx-4070-ti-super","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,14080,false,62,null,null],["nvidia-geforce-rtx-4070-ti-super","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q2_K",8192,11.09,18944,false,67.2,null,null],["nvidia-geforce-rtx-4070-ti-super","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,24576,false,60.3,null,null],["nvidia-geforce-rtx-4070-ti-super","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,193.5,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,61.6,null,null],["nvidia-geforce-rtx-4070-ti-super","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","north-mini-code-1-0","cuda","fits","IQ2_M",8192,12.7,9728,false,316.1,null,null],["nvidia-geforce-rtx-4070-ti-super","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"7",null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,237312,false,92.5,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,75,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,67.7,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,8448,false,67.2,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,12032,false,67.7,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,67.7,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,12032,false,67.7,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,8448,false,67.2,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,8448,false,67.2,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,11520,false,80.6,null,null],["nvidia-geforce-rtx-4070-ti-super","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","optimind-sft","cuda","tight","Q5_K_M",8192,17.77,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,19712,false,93.6,null,null],["nvidia-geforce-rtx-4070-ti-super","phi-4","cuda","fits","Q5_K_M",8192,12.78,8448,false,57.3,null,null],["nvidia-geforce-rtx-4070-ti-super","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,30208,false,76.8,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,9216,false,58,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,187.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,72192,false,84.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,315.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-30b-a3b-instruct-2507","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,122.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,418.3,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,934.1,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,173.8,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,408.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-35b-a3b-base","cuda","fits","IQ2_XXS",8192,10.92,96512,false,544.5,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-4b","cuda","fits","BF16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,84736,false,77.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,84736,false,77.2,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-6-35b-a3b","cuda","fits","IQ2_XXS",8192,11.35,77056,false,407.3,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-8-27b","cuda","fits","Q2_K",8192,12.48,14080,false,63.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-8-3-6-27b-blend","cuda","fits","Q2_K",8192,12.48,14080,false,63.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-reap-25b-a3b","cuda","fits","IQ3_XXS",8192,11.77,19200,false,297.9,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-4070-ti-super","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,140.3,null,null],["nvidia-geforce-rtx-4070-ti-super","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,22528,false,67.8,null,null],["nvidia-geforce-rtx-4070-ti-super","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,61.6,null,null],["nvidia-geforce-rtx-4070-ti-super","singguard-2b","cuda","fits","F16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,99.5,null,null],["nvidia-geforce-rtx-4070-ti-super","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,214.9,null,null],["nvidia-geforce-rtx-4070-ti-super","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,100864,false,107.2,null,null],["nvidia-geforce-rtx-4070-ti-super","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"5",null],["nvidia-geforce-rtx-4070-ti-super","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-4070-ti-super","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-4070-ti-super","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8",null],["nvidia-geforce-rtx-4070-ti-super","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","tiny-aya-earth","cuda","fits","BF16",8192,8.72,190720,false,95,null,null],["nvidia-geforce-rtx-4070-ti-super","tiny-aya-fire","cuda","fits","BF16",8192,8.72,190720,false,95,null,null],["nvidia-geforce-rtx-4070-ti-super","tiny-aya-global","cuda","fits","BF16",8192,8.72,190720,false,95,null,null],["nvidia-geforce-rtx-4070-ti-super","tiny-aya-water","cuda","fits","BF16",8192,8.72,190720,false,95,null,null],["nvidia-geforce-rtx-4070-ti-super","translategemma-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,72.2,null,null],["nvidia-geforce-rtx-4070-ti-super","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,83.5,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4070-ti-super","trinity-mini","cuda","fits","IQ3_XXS",8192,12.12,48640,false,382.3,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,68096,false,430.2,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-mini-base-pre-anneal","cuda","fits","IQ3_XXS",4096,11.48,4096,false,449.5,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,746.2,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,798.2,null,null],["nvidia-geforce-rtx-4070-ti-super","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,131072,false,612.5,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-mate-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,63.3,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,84224,false,77,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,10240,false,62.1,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-venus-1-5-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4070-ti-super","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,84224,false,77,null,null],["nvidia-geforce-rtx-4070-ti-super","userrepgen-4b","cuda","fits","BF16",8192,10.23,85504,false,77.4,null,null],["nvidia-geforce-rtx-4070-ti-super","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,59.4,null,null],["nvidia-geforce-rtx-4070-ti-super","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,61.6,null,null],["nvidia-geforce-rtx-4070-ti-super","webworld-8b","cuda","fits","Q8_0",8192,10.39,25088,false,72.6,null,null],["nvidia-geforce-rtx-4070-ti-super","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,100864,false,107.2,null,null],["nvidia-geforce-rtx-4070-ti-super","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,350,null,null],["nvidia-geforce-rtx-4070-ti-super","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,350,null,null],["nvidia-geforce-rtx-4070-ti-super","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,152.2,null,null],["nvidia-geforce-rtx-4070-ti-super","zwz-2b","cuda","fits","F16",8192,5.62,71424,false,153.4,null,null],["nvidia-geforce-rtx-4070-ti-super","zwz-4b","cuda","fits","Q6_K",8192,5.74,56832,false,149.1,null,null],["nvidia-geforce-rtx-4070-ti-super","zwz-7b","cuda","fits","Q6_K",8192,7.47,100864,false,107.2,null,null],["nvidia-geforce-rtx-4070-ti-super","zwz-8b","cuda","fits","Q6_K",8192,8.59,37376,false,90.6,null,null],["nvidia-geforce-rtx-4080","aescode-32b","cuda","tight","Q3_K_M",8192,19.28,null,null,null,null,null],["nvidia-geforce-rtx-4080","aescode-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,56832,false,159,null,null],["nvidia-geforce-rtx-4080","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,118.1,null,null],["nvidia-geforce-rtx-4080","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,118.1,null,null],["nvidia-geforce-rtx-4080","ai21-jamba2-mini","cuda","tight","Q2_K",8192,19.01,null,null,null,null,null],["nvidia-geforce-rtx-4080","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,273.9,null,null],["nvidia-geforce-rtx-4080","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,273.9,null,null],["nvidia-geforce-rtx-4080","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,223.3,null,null],["nvidia-geforce-rtx-4080","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,10240,false,62.8,null,null],["nvidia-geforce-rtx-4080","aprielguard","cuda","fits","Q6_K",8192,7.87,58880,false,106.6,null,null],["nvidia-geforce-rtx-4080","armorocr","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","astabrief-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,57344,false,74.2,null,null],["nvidia-geforce-rtx-4080","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,88.7,null,null],["nvidia-geforce-rtx-4080","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4080","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-4080","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,13312,false,66.8,null,null],["nvidia-geforce-rtx-4080","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,24320,false,78.4,null,null],["nvidia-geforce-rtx-4080","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,233.4,null,null],["nvidia-geforce-rtx-4080","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-4080","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"7",null],["nvidia-geforce-rtx-4080","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,9472,false,62.1,null,null],["nvidia-geforce-rtx-4080","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","contextpilot-e4b","cuda","fits","F16",8192,10.89,118016,false,75.9,null,null],["nvidia-geforce-rtx-4080","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,65.7,null,null],["nvidia-geforce-rtx-4080","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,129.7,null,null],["nvidia-geforce-rtx-4080","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-4080","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4080","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,28928,false,79.2,null,null],["nvidia-geforce-rtx-4080","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,9216,false,61.9,null,null],["nvidia-geforce-rtx-4080","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4080","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-4080","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-4080","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-4080","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-4080","devstral-small-2-24b-instruct-2512","cuda","fits","Q2_K",8192,11.09,18944,false,71.7,null,null],["nvidia-geforce-rtx-4080","eurollm-22b-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,68.8,null,null],["nvidia-geforce-rtx-4080","eurollm-22b-instruct-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,68.8,null,null],["nvidia-geforce-rtx-4080","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,15360,false,67.8,null,null],["nvidia-geforce-rtx-4080","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1166.5,null,null],["nvidia-geforce-rtx-4080","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-4080","fara-7b","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","fara1-5-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,67.6,null,null],["nvidia-geforce-rtx-4080","fara1-5-4b","cuda","fits","BF16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,84224,false,82.2,null,null],["nvidia-geforce-rtx-4080","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,11264,false,65.7,null,null],["nvidia-geforce-rtx-4080","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","frognano-4b-2609","cuda","fits","BF16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1259.4,null,null],["nvidia-geforce-rtx-4080","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","gemma-2-27b-it","cuda","tight","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,72.3,null,null],["nvidia-geforce-rtx-4080","gemma-3-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,77,null,null],["nvidia-geforce-rtx-4080","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,350.6,null,null],["nvidia-geforce-rtx-4080","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,89.1,null,null],["nvidia-geforce-rtx-4080","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,15360,false,70,null,null],["nvidia-geforce-rtx-4080","gemma-4-26b-a4b","cuda","tight","Q4_K_M",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-4-26b-a4b-it","cuda","fits","IQ2_XXS",8192,12.09,43520,false,313.1,null,null],["nvidia-geforce-rtx-4080","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-4080","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,365.9,null,null],["nvidia-geforce-rtx-4080","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,154,null,null],["nvidia-geforce-rtx-4080","gemma-4-e4b","cuda","fits","F16",8192,11,111872,false,75,null,null],["nvidia-geforce-rtx-4080","gemma-4-e4b-it","cuda","fits","BF16",8192,11,111872,false,75,null,null],["nvidia-geforce-rtx-4080","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-4080","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-4080","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-4080","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,57344,false,74.2,null,null],["nvidia-geforce-rtx-4080","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,9984,false,319.2,null,null],["nvidia-geforce-rtx-4080","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,11776,false,286.7,null,null],["nvidia-geforce-rtx-4080","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-4080","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-4080","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-4080","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-4080","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4080","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-4080","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-4080","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"7",null],["nvidia-geforce-rtx-4080","gpt-oss-20b","cuda","fits","Q6_K",8192,12.83,9728,false,264.5,null,null],["nvidia-geforce-rtx-4080","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,18944,false,71.5,null,null],["nvidia-geforce-rtx-4080","granite-4-0-1b","cuda","fits","BF16",8192,5.14,102144,false,182.2,null,null],["nvidia-geforce-rtx-4080","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,763,null,null],["nvidia-geforce-rtx-4080","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,239.6,null,null],["nvidia-geforce-rtx-4080","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1002.9,null,null],["nvidia-geforce-rtx-4080","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4080","granite-4-1-3b","cuda","fits","BF16",8192,8.61,59904,false,95.9,null,null],["nvidia-geforce-rtx-4080","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,70,null,null],["nvidia-geforce-rtx-4080","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-4080","granite-4-2-3b","cuda","fits","BF16",8192,8.61,59904,false,95.9,null,null],["nvidia-geforce-rtx-4080","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,17664,false,70,null,null],["nvidia-geforce-rtx-4080","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,18944,false,71.5,null,null],["nvidia-geforce-rtx-4080","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,107776,false,207,null,null],["nvidia-geforce-rtx-4080","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,70,null,null],["nvidia-geforce-rtx-4080","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,59904,false,95.9,null,null],["nvidia-geforce-rtx-4080","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,99.2,null,null],["nvidia-geforce-rtx-4080","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,114.3,null,null],["nvidia-geforce-rtx-4080","hermes-4-3-36b","cuda","tight","IQ3_XXS",8192,16.93,null,null,null,null,null],["nvidia-geforce-rtx-4080","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,304.9,null,null],["nvidia-geforce-rtx-4080","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,996.6,null,null],["nvidia-geforce-rtx-4080","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4080","holo-3-1-4b","cuda","fits","F16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,84736,false,82.4,null,null],["nvidia-geforce-rtx-4080","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4080","holo2-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-4080","holo2-4b","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","holo2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-4080","holo4-27b","cuda","fits","Q2_K",8192,12.74,10240,false,66.3,null,null],["nvidia-geforce-rtx-4080","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,48640,false,418.2,null,null],["nvidia-geforce-rtx-4080","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4080","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,380.7,null,null],["nvidia-geforce-rtx-4080","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8",null],["nvidia-geforce-rtx-4080","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,28928,false,79.2,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,28928,false,79.2,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,28928,false,79.2,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,28928,false,79.2,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","ising-calibration-1-35b-a3b","cuda","fits","IQ2_XXS",8192,11.07,89600,false,516.8,null,null],["nvidia-geforce-rtx-4080","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-4080","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","januscoder-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,194.7,null,null],["nvidia-geforce-rtx-4080","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,96.4,null,null],["nvidia-geforce-rtx-4080","kat-coder-v2-5-dev","cuda","fits","IQ2_XXS",8192,11.35,77056,false,434.5,null,null],["nvidia-geforce-rtx-4080","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-4080","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-4080","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-4080","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-4080","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-4080","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-4080","kimi-linear-48b-a3b-instruct","cuda","tight","Q2_K",8192,18.65,null,null,null,null,null],["nvidia-geforce-rtx-4080","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,14848,false,539.4,null,null],["nvidia-geforce-rtx-4080","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","laguna-xs-2-1","cuda","fits","IQ2_XXS",8192,11.07,50944,false,393.3,null,null],["nvidia-geforce-rtx-4080","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,136,null,null],["nvidia-geforce-rtx-4080","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,136,null,null],["nvidia-geforce-rtx-4080","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,136,null,null],["nvidia-geforce-rtx-4080","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-4080","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,129.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,305.4,null,null],["nvidia-geforce-rtx-4080","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1280,null,null],["nvidia-geforce-rtx-4080","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-4080","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,885.4,null,null],["nvidia-geforce-rtx-4080","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,378.1,null,null],["nvidia-geforce-rtx-4080","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1830.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,293.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,129.7,null,null],["nvidia-geforce-rtx-4080","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,885.4,null,null],["nvidia-geforce-rtx-4080","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,885.4,null,null],["nvidia-geforce-rtx-4080","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,407.2,null,null],["nvidia-geforce-rtx-4080","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,136,null,null],["nvidia-geforce-rtx-4080","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-4080","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-4080","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,99.2,null,null],["nvidia-geforce-rtx-4080","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,261.7,null,null],["nvidia-geforce-rtx-4080","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,46336,false,97.3,null,null],["nvidia-geforce-rtx-4080","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-4080","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-4080","mathform-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,89.1,null,null],["nvidia-geforce-rtx-4080","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,57600,false,341.1,null,null],["nvidia-geforce-rtx-4080","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,57600,false,341.1,null,null],["nvidia-geforce-rtx-4080","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,50688,false,323.8,null,null],["nvidia-geforce-rtx-4080","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,57600,false,341.1,null,null],["nvidia-geforce-rtx-4080","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,50688,false,323.8,null,null],["nvidia-geforce-rtx-4080","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,57600,false,341.1,null,null],["nvidia-geforce-rtx-4080","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,40448,false,103.1,null,null],["nvidia-geforce-rtx-4080","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-4080","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,84224,false,82.2,null,null],["nvidia-geforce-rtx-4080","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4080","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-4080","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,446.5,null,null],["nvidia-geforce-rtx-4080","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,446.5,null,null],["nvidia-geforce-rtx-4080","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,446.5,null,null],["nvidia-geforce-rtx-4080","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-4080","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,776.4,null,null],["nvidia-geforce-rtx-4080","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,776.4,null,null],["nvidia-geforce-rtx-4080","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,776.4,null,null],["nvidia-geforce-rtx-4080","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,147.8,null,null],["nvidia-geforce-rtx-4080","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,221696,false,326.2,null,null],["nvidia-geforce-rtx-4080","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4080","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4080","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-4080","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-4080","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-4080","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,68.3,null,null],["nvidia-geforce-rtx-4080","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,68.3,null,null],["nvidia-geforce-rtx-4080","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,45824,false,92.7,null,null],["nvidia-geforce-rtx-4080","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,45824,false,92.7,null,null],["nvidia-geforce-rtx-4080","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,23808,false,74.8,null,null],["nvidia-geforce-rtx-4080","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,23808,false,74.8,null,null],["nvidia-geforce-rtx-4080","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,103.8,null,null],["nvidia-geforce-rtx-4080","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-4080","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-4080","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,14080,false,66.1,null,null],["nvidia-geforce-rtx-4080","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q2_K",8192,11.09,18944,false,71.7,null,null],["nvidia-geforce-rtx-4080","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-4080","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,24576,false,64.3,null,null],["nvidia-geforce-rtx-4080","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-4080","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,206.4,null,null],["nvidia-geforce-rtx-4080","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["nvidia-geforce-rtx-4080","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-4080","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,65.7,null,null],["nvidia-geforce-rtx-4080","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","north-mini-code-1-0","cuda","fits","IQ2_M",8192,12.7,9728,false,337.2,null,null],["nvidia-geforce-rtx-4080","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"7",null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,237312,false,98.7,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"5",null],["nvidia-geforce-rtx-4080","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-4080","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-4080","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,80,null,null],["nvidia-geforce-rtx-4080","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4080","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,72.2,null,null],["nvidia-geforce-rtx-4080","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4080","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,8448,false,71.7,null,null],["nvidia-geforce-rtx-4080","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,12032,false,72.2,null,null],["nvidia-geforce-rtx-4080","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-4080","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,72.2,null,null],["nvidia-geforce-rtx-4080","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,12032,false,72.2,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,8448,false,71.7,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,8448,false,71.7,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,11520,false,86,null,null],["nvidia-geforce-rtx-4080","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","optimind-sft","cuda","tight","Q5_K_M",8192,17.77,null,null,null,null,null],["nvidia-geforce-rtx-4080","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,19712,false,99.9,null,null],["nvidia-geforce-rtx-4080","phi-4","cuda","fits","Q5_K_M",8192,12.78,8448,false,61.1,null,null],["nvidia-geforce-rtx-4080","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,30208,false,82,null,null],["nvidia-geforce-rtx-4080","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"4",null],["nvidia-geforce-rtx-4080","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,9216,false,61.9,null,null],["nvidia-geforce-rtx-4080","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,200.2,null,null],["nvidia-geforce-rtx-4080","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-4080","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,89.8,null,null],["nvidia-geforce-rtx-4080","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,89.8,null,null],["nvidia-geforce-rtx-4080","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,72192,false,89.8,null,null],["nvidia-geforce-rtx-4080","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,336.3,null,null],["nvidia-geforce-rtx-4080","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,163.7,null,null],["nvidia-geforce-rtx-4080","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4080","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-4080","qwen3-30b-a3b-instruct-2507","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-4080","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,130.8,null,null],["nvidia-geforce-rtx-4080","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,446.3,null,null],["nvidia-geforce-rtx-4080","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,996.6,null,null],["nvidia-geforce-rtx-4080","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["nvidia-geforce-rtx-4080","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,185.5,null,null],["nvidia-geforce-rtx-4080","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,435.6,null,null],["nvidia-geforce-rtx-4080","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-5-35b-a3b-base","cuda","fits","IQ2_XXS",8192,10.92,96512,false,581,null,null],["nvidia-geforce-rtx-4080","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-4080","qwen3-5-4b","cuda","fits","BF16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,84736,false,82.4,null,null],["nvidia-geforce-rtx-4080","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,84736,false,82.4,null,null],["nvidia-geforce-rtx-4080","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-6-35b-a3b","cuda","fits","IQ2_XXS",8192,11.35,77056,false,434.6,null,null],["nvidia-geforce-rtx-4080","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-4080","qwen3-8-27b","cuda","fits","Q2_K",8192,12.48,14080,false,67.9,null,null],["nvidia-geforce-rtx-4080","qwen3-8-3-6-27b-blend","cuda","fits","Q2_K",8192,12.48,14080,false,67.9,null,null],["nvidia-geforce-rtx-4080","qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwen3-coder-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-4080","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-4080","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-4080","qwen3-coder-reap-25b-a3b","cuda","fits","IQ3_XXS",8192,11.77,19200,false,317.8,null,null],["nvidia-geforce-rtx-4080","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-4080","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-4080","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-4080","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-4080","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,149.7,null,null],["nvidia-geforce-rtx-4080","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,22528,false,72.4,null,null],["nvidia-geforce-rtx-4080","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,65.7,null,null],["nvidia-geforce-rtx-4080","singguard-2b","cuda","fits","F16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,106.2,null,null],["nvidia-geforce-rtx-4080","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,229.3,null,null],["nvidia-geforce-rtx-4080","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-4080","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,100864,false,114.3,null,null],["nvidia-geforce-rtx-4080","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"5",null],["nvidia-geforce-rtx-4080","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-4080","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-4080","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8",null],["nvidia-geforce-rtx-4080","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","tiny-aya-earth","cuda","fits","BF16",8192,8.72,190720,false,101.3,null,null],["nvidia-geforce-rtx-4080","tiny-aya-fire","cuda","fits","BF16",8192,8.72,190720,false,101.3,null,null],["nvidia-geforce-rtx-4080","tiny-aya-global","cuda","fits","BF16",8192,8.72,190720,false,101.3,null,null],["nvidia-geforce-rtx-4080","tiny-aya-water","cuda","fits","BF16",8192,8.72,190720,false,101.3,null,null],["nvidia-geforce-rtx-4080","translategemma-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,77,null,null],["nvidia-geforce-rtx-4080","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-4080","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,89.1,null,null],["nvidia-geforce-rtx-4080","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-4080","trinity-mini","cuda","fits","IQ3_XXS",8192,12.12,48640,false,407.9,null,null],["nvidia-geforce-rtx-4080","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,68096,false,459,null,null],["nvidia-geforce-rtx-4080","trinity-mini-base-pre-anneal","cuda","fits","IQ3_XXS",4096,11.48,4096,false,479.6,null,null],["nvidia-geforce-rtx-4080","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,796.1,null,null],["nvidia-geforce-rtx-4080","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,851.7,null,null],["nvidia-geforce-rtx-4080","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,131072,false,653.5,null,null],["nvidia-geforce-rtx-4080","ui-mate-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,67.6,null,null],["nvidia-geforce-rtx-4080","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,84224,false,82.2,null,null],["nvidia-geforce-rtx-4080","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,10240,false,66.3,null,null],["nvidia-geforce-rtx-4080","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","ui-venus-1-5-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-4080","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-4080","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,84224,false,82.2,null,null],["nvidia-geforce-rtx-4080","userrepgen-4b","cuda","fits","BF16",8192,10.23,85504,false,82.6,null,null],["nvidia-geforce-rtx-4080","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,63.4,null,null],["nvidia-geforce-rtx-4080","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,65.7,null,null],["nvidia-geforce-rtx-4080","webworld-8b","cuda","fits","Q8_0",8192,10.39,25088,false,77.5,null,null],["nvidia-geforce-rtx-4080","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,100864,false,114.3,null,null],["nvidia-geforce-rtx-4080","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,373.5,null,null],["nvidia-geforce-rtx-4080","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,373.5,null,null],["nvidia-geforce-rtx-4080","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,162.4,null,null],["nvidia-geforce-rtx-4080","zwz-2b","cuda","fits","F16",8192,5.62,71424,false,163.7,null,null],["nvidia-geforce-rtx-4080","zwz-4b","cuda","fits","Q6_K",8192,5.74,56832,false,159,null,null],["nvidia-geforce-rtx-4080","zwz-7b","cuda","fits","Q6_K",8192,7.47,100864,false,114.3,null,null],["nvidia-geforce-rtx-4080","zwz-8b","cuda","fits","Q6_K",8192,8.59,37376,false,96.7,null,null],["nvidia-geforce-rtx-5060","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,"4",null],["nvidia-geforce-rtx-5060","aescode-8b","cuda","fits","IQ2_M",8192,5.32,8960,false,110,null,null],["nvidia-geforce-rtx-5060","agentcpm-explore","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","ai21-jamba-reasoning-3b","cuda","fits","Q8_0",8192,4.49,262144,false,138.4,null,null],["nvidia-geforce-rtx-5060","ai21-jamba2-3b","cuda","fits","Q8_0",8192,4.49,262144,false,138.4,null,null],["nvidia-geforce-rtx-5060","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,"4",null],["nvidia-geforce-rtx-5060","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-5060","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,171.2,null,null],["nvidia-geforce-rtx-5060","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,139.5,null,null],["nvidia-geforce-rtx-5060","apriel-1-6-15b-thinker","cuda","tight","IQ4_XS",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-5060","aprielguard","cuda","fits","IQ3_XXS",8192,4.98,12544,false,118.5,null,null],["nvidia-geforce-rtx-5060","armorocr","cuda","tight","Q4_K_M",8192,7.09,null,null,null,null,null],["nvidia-geforce-rtx-5060","astabrief-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","autoglm-phone-9b","cuda","fits","Q2_K",8192,5.37,9728,false,108.5,null,null],["nvidia-geforce-rtx-5060","autoglm-phone-9b-multilingual","cuda","fits","Q2_K",8192,5.37,9728,false,108.5,null,null],["nvidia-geforce-rtx-5060","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5060","bielik-11b-v3-0-instruct","cuda","tight","Q4_K_M",8192,9.44,null,null,null,null,null],["nvidia-geforce-rtx-5060","bielik-minitron-7b-v3-0-instruct","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-5060","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,145.8,null,null],["nvidia-geforce-rtx-5060","caprl-qwen3vl-2b","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","caprl-qwen3vl-4b","cuda","fits","Q4_K_M",8192,4.95,11520,false,121.1,null,null],["nvidia-geforce-rtx-5060","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-5060","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","contextpilot-14b","cuda","tight","Q3_K_M",8192,9.69,null,null,null,null,null],["nvidia-geforce-rtx-5060","contextpilot-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","contextpilot-e4b","cuda","fits","Q5_K_M",8192,5.11,26112,false,126.2,null,null],["nvidia-geforce-rtx-5060","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"3",null],["nvidia-geforce-rtx-5060","cosmos-reason2-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","d1-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-5060","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-5060","deepseek-r1-0528-qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"8",null],["nvidia-geforce-rtx-5060","deepseek-r1-distill-llama-8b","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","deepseek-r1-distill-qwen-14b","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-5060","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"4",null],["nvidia-geforce-rtx-5060","deepseek-r1-distill-qwen-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-5060","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-5060","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-5060","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-5060","eurollm-22b-2512","cuda","tight","IQ2_XXS",8192,9.06,null,null,null,null,null],["nvidia-geforce-rtx-5060","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,"3",null],["nvidia-geforce-rtx-5060","eurollm-9b-instruct-2512","cuda","tight","Q6_K",8192,9.6,null,null,null,null,null],["nvidia-geforce-rtx-5060","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,728.8,null,null],["nvidia-geforce-rtx-5060","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"6",null],["nvidia-geforce-rtx-5060","fara-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,"4",null],["nvidia-geforce-rtx-5060","fara1-5-4b","cuda","fits","Q5_K_M",8192,5.22,14336,false,125.4,null,null],["nvidia-geforce-rtx-5060","fara1-5-9b","cuda","fits","IQ2_M",8192,5.24,13824,false,124.8,null,null],["nvidia-geforce-rtx-5060","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"3",null],["nvidia-geforce-rtx-5060","frogmini-14b-2510","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","frognano-4b-2609","cuda","fits","Q5_K_M",8192,5.2,14848,false,126.2,null,null],["nvidia-geforce-rtx-5060","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,786.9,null,null],["nvidia-geforce-rtx-5060","gelab-zero-4b-preview","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,"4",null],["nvidia-geforce-rtx-5060","gemma-2-9b-it","cuda","tight","Q5_K_M",8192,10.82,null,null,null,null,null],["nvidia-geforce-rtx-5060","gemma-3-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-5060","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,219.1,null,null],["nvidia-geforce-rtx-5060","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"4",null],["nvidia-geforce-rtx-5060","gemma-3-4b-it","cuda","fits","Q6_K",8192,5.37,11008,false,129,null,null],["nvidia-geforce-rtx-5060","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,"5",null],["nvidia-geforce-rtx-5060","gemma-4-12b-it","cuda","tight","Q4_K_M",8192,10.13,null,null,null,null,null],["nvidia-geforce-rtx-5060","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,"4",null],["nvidia-geforce-rtx-5060","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,"3",null],["nvidia-geforce-rtx-5060","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"6",null],["nvidia-geforce-rtx-5060","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"6",null],["nvidia-geforce-rtx-5060","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,228.6,null,null],["nvidia-geforce-rtx-5060","gemma-4-e2b-it","cuda","fits","Q8_0",8192,4.12,131072,false,172.7,null,null],["nvidia-geforce-rtx-5060","gemma-4-e4b","cuda","fits","Q5_K_M",8192,5.15,24064,false,124.8,null,null],["nvidia-geforce-rtx-5060","gemma-4-e4b-it","cuda","fits","Q5_K_M",8192,5.24,18944,false,121.6,null,null],["nvidia-geforce-rtx-5060","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","glm-4-6v-flash","cuda","fits","Q2_K",8192,5.37,9728,false,108.5,null,null],["nvidia-geforce-rtx-5060","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,"4",null],["nvidia-geforce-rtx-5060","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q2_K",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-5060","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5060","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-geforce-rtx-5060","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,"3",null],["nvidia-geforce-rtx-5060","granite-3-3-8b-instruct","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-5060","granite-4-0-1b","cuda","fits","BF16",8192,5.14,11776,false,113.9,null,null],["nvidia-geforce-rtx-5060","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,476.7,null,null],["nvidia-geforce-rtx-5060","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,107520,false,149.7,null,null],["nvidia-geforce-rtx-5060","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,626.6,null,null],["nvidia-geforce-rtx-5060","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-5060","granite-4-1-3b","cuda","fits","Q6_K",8192,4.67,17408,false,129.4,null,null],["nvidia-geforce-rtx-5060","granite-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-5060","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,"4",null],["nvidia-geforce-rtx-5060","granite-4-2-3b","cuda","fits","Q6_K",8192,4.67,17408,false,129.4,null,null],["nvidia-geforce-rtx-5060","granite-4-2-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-5060","granite-guardian-3-2-8b-factuality-detection","cuda","tight","Q6_K",8192,9.17,null,null,null,null,null],["nvidia-geforce-rtx-5060","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,17408,false,129.4,null,null],["nvidia-geforce-rtx-5060","granite-guardian-4-1-8b","cuda","tight","Q6_K",8192,9.34,null,null,null,null,null],["nvidia-geforce-rtx-5060","granite-vision-4-1-4b","cuda","fits","Q6_K",8192,4.67,17408,false,129.4,null,null],["nvidia-geforce-rtx-5060","harc-llama-3-1-8b-instruct","cuda","fits","IQ3_XXS",8192,5.31,8960,false,108.9,null,null],["nvidia-geforce-rtx-5060","harc-qwen2-5-7b-instruct","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,"3",null],["nvidia-geforce-rtx-5060","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,23808,false,190.5,null,null],["nvidia-geforce-rtx-5060","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,231424,false,622.7,null,null],["nvidia-geforce-rtx-5060","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-5060","holo-3-1-4b","cuda","fits","Q6_K",8192,5.37,9984,false,120.4,null,null],["nvidia-geforce-rtx-5060","holo-3-1-9b","cuda","fits","Q2_K",8192,5.4,9216,false,119.4,null,null],["nvidia-geforce-rtx-5060","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-5060","holo2-4b","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","holo2-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,"4",null],["nvidia-geforce-rtx-5060","holo4-27b","cuda","tight","IQ2_XXS",8192,10.5,null,null,null,null,null],["nvidia-geforce-rtx-5060","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,"3",null],["nvidia-geforce-rtx-5060","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"5",null],["nvidia-geforce-rtx-5060","hunyuanocr","cuda","fits","F16",8192,3.13,31488,false,237.9,null,null],["nvidia-geforce-rtx-5060","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-geforce-rtx-5060","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-8b-baseline","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","intent-aware-lfqa-qwen3-8b-multiview","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-5060","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-5060","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,"5",null],["nvidia-geforce-rtx-5060","januscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","januscoder-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","januscoderv-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-5060","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,12288,false,121.6,null,null],["nvidia-geforce-rtx-5060","kanana-2-3b-instruct","cuda","fits","Q6_K",8192,4.89,12288,false,121.6,null,null],["nvidia-geforce-rtx-5060","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-5060","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"8",null],["nvidia-geforce-rtx-5060","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5060","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-5060","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5060","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5060","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,"4",null],["nvidia-geforce-rtx-5060","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,"4",null],["nvidia-geforce-rtx-5060","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,"3",null],["nvidia-geforce-rtx-5060","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-geforce-rtx-5060","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,"3",null],["nvidia-geforce-rtx-5060","lfm2-2-6b-exp","cuda","fits","Q8_0",8192,4.09,82688,false,156.4,null,null],["nvidia-geforce-rtx-5060","lfm2-2-6b-longevity","cuda","fits","Q8_0",8192,4.09,82688,false,156.4,null,null],["nvidia-geforce-rtx-5060","lfm2-2-6b-transcript","cuda","fits","Q8_0",8192,4.09,82688,false,156.4,null,null],["nvidia-geforce-rtx-5060","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,"4",null],["nvidia-geforce-rtx-5060","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-2-6b","cuda","fits","Q8_0",8192,4.22,75264,false,149.3,null,null],["nvidia-geforce-rtx-5060","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,110848,false,190.8,null,null],["nvidia-geforce-rtx-5060","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,799.8,null,null],["nvidia-geforce-rtx-5060","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,"4",null],["nvidia-geforce-rtx-5060","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-5060","lfm2-5-8b-a1b","cuda","tight","Q8_0",8192,10.2,null,null,null,null,null],["nvidia-geforce-rtx-5060","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1143.9,null,null],["nvidia-geforce-rtx-5060","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,183.5,null,null],["nvidia-geforce-rtx-5060","lfm2-5-vl-3b","cuda","fits","Q8_0",8192,4.22,32768,false,149.3,null,null],["nvidia-geforce-rtx-5060","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-5060","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,553.2,null,null],["nvidia-geforce-rtx-5060","lfm2-8b-a1b","cuda","tight","Q8_0",8192,10.07,null,null,null,null,null],["nvidia-geforce-rtx-5060","lfm2-vl-3b","cuda","fits","Q8_0",8192,4.09,82688,false,156.4,null,null],["nvidia-geforce-rtx-5060","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5060","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"6",null],["nvidia-geforce-rtx-5060","llama-3-1-8b-instruct","cuda","fits","Q2_K",8192,5.27,9216,false,110,null,null],["nvidia-geforce-rtx-5060","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,51200,false,163.5,null,null],["nvidia-geforce-rtx-5060","llama-3-2-3b-instruct","cuda","fits","Q6_K",8192,4.78,13824,false,125.3,null,null],["nvidia-geforce-rtx-5060","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"8",null],["nvidia-geforce-rtx-5060","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","mathform-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","medgemma-1-5-4b-it","cuda","fits","Q6_K",8192,5.37,11008,false,129,null,null],["nvidia-geforce-rtx-5060","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-5060","mellum2-12b-a2-5b-base","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-5060","mellum2-12b-a2-5b-instruct","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-5060","mellum2-12b-a2-5b-instruct-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-5060","mellum2-12b-a2-5b-thinking","cuda","tight","Q4_K_M",8192,9.48,null,null,null,null,null],["nvidia-geforce-rtx-5060","mellum2-12b-a2-5b-thinking-sft","cuda","tight","Q4_K_M",8192,9.38,null,null,null,null,null],["nvidia-geforce-rtx-5060","mimo-embodied-7b","cuda","fits","IQ3_XXS",8192,5.33,8704,false,109.6,null,null],["nvidia-geforce-rtx-5060","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-6-distill-qwen-9b","cuda","fits","Q2_K",8192,5.12,17408,false,129.3,null,null],["nvidia-geforce-rtx-5060","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-5060","minicpm-o-4-5","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","minicpm-v-4-6","cuda","fits","F16",8192,3.17,169472,false,279,null,null],["nvidia-geforce-rtx-5060","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,169472,false,279,null,null],["nvidia-geforce-rtx-5060","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,169472,false,279,null,null],["nvidia-geforce-rtx-5060","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"5",null],["nvidia-geforce-rtx-5060","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,485.1,null,null],["nvidia-geforce-rtx-5060","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,485.1,null,null],["nvidia-geforce-rtx-5060","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,485.1,null,null],["nvidia-geforce-rtx-5060","minicpm5-2b","cuda","fits","Q8_0",8192,3.97,41216,false,163.3,null,null],["nvidia-geforce-rtx-5060","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,53504,false,203.8,null,null],["nvidia-geforce-rtx-5060","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-5060","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-5060","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-geforce-rtx-5060","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-5060","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,"3",null],["nvidia-geforce-rtx-5060","ministral-3-3b-instruct-2512","cuda","fits","Q5_K_M",8192,4.55,16384,false,134.2,null,null],["nvidia-geforce-rtx-5060","ministral-3-3b-reasoning-2512","cuda","fits","Q5_K_M",8192,4.55,16384,false,134.2,null,null],["nvidia-geforce-rtx-5060","ministral-3-8b-instruct-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-5060","ministral-3-8b-reasoning-2512","cuda","tight","Q5_K_M",8192,7.97,null,null,null,null,null],["nvidia-geforce-rtx-5060","mistral-7b-instruct-v0-2","cuda","fits","IQ3_XXS",8192,5.05,11008,false,116.5,null,null],["nvidia-geforce-rtx-5060","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-5060","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","mistral-nemo-instruct-2407","cuda","tight","Q4_K_M",8192,9.55,null,null,null,null,null],["nvidia-geforce-rtx-5060","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,"3",null],["nvidia-geforce-rtx-5060","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","muse-glimmer-30b","cuda","tight","IQ2_XXS",8192,10.17,null,null,null,null,null],["nvidia-geforce-rtx-5060","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5060","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,11008,false,129,null,null],["nvidia-geforce-rtx-5060","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"6",null],["nvidia-geforce-rtx-5060","nemotron-cascade-14b-thinking","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"6",null],["nvidia-geforce-rtx-5060","nemotron-cascade-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","nemotron-cascade-8b-thinking","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","nemotron-orchestrator-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","nemotron-terminal-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"3",null],["nvidia-geforce-rtx-5060","nemotron-terminal-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,"3",null],["nvidia-geforce-rtx-5060","nouscoder-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"5",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"5",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"5",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","Q6_K",8192,5.29,16384,false,119.6,null,null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"5",null],["nvidia-geforce-rtx-5060","nvidia-nemotron-nano-9b-v2","cuda","tight","Q8_0",8192,10.63,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,"4",null],["nvidia-geforce-rtx-5060","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"3",null],["nvidia-geforce-rtx-5060","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"4",null],["nvidia-geforce-rtx-5060","olmo-3-1-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-1-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"3",null],["nvidia-geforce-rtx-5060","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,"4",null],["nvidia-geforce-rtx-5060","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"3",null],["nvidia-geforce-rtx-5060","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,"3",null],["nvidia-geforce-rtx-5060","olmo-3-7b-instruct","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-instruct-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-instruct-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-rl-zero-code","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-rl-zero-general","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-rl-zero-if","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-rl-zero-math","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-rl-zero-mix","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-think","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-think-dpo","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmo-3-7b-think-sft","cuda","tight","Q6_K",8192,11.05,null,null,null,null,null],["nvidia-geforce-rtx-5060","olmocr-2-7b-1025","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,"4",null],["nvidia-geforce-rtx-5060","phi-3-5-mini-instruct","cuda","tight","Q8_0",8192,8.32,null,null,null,null,null],["nvidia-geforce-rtx-5060","phi-4","cuda","tight","Q3_K_M",8192,9.75,null,null,null,null,null],["nvidia-geforce-rtx-5060","phi-4-mini-instruct","cuda","fits","Q5_K_M",8192,5.25,9472,false,114.5,null,null],["nvidia-geforce-rtx-5060","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen2-5-14b-instruct","cuda","tight","Q3_K_M",8192,9.76,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"4",null],["nvidia-geforce-rtx-5060","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,23808,false,125.1,null,null],["nvidia-geforce-rtx-5060","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen2-5-7b-instruct","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"4",null],["nvidia-geforce-rtx-5060","qwen2-5-coder-7b-instruct","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","qwen2-5-vl-7b-instruct","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","qwen3-0-6b","cuda","fits","BF16",8192,3.41,25856,false,210.2,null,null],["nvidia-geforce-rtx-5060","qwen3-1-7b","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"5",null],["nvidia-geforce-rtx-5060","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"6",null],["nvidia-geforce-rtx-5060","qwen3-4b","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","qwen3-4b-instruct-2507","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,169472,false,278.9,null,null],["nvidia-geforce-rtx-5060","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,231424,false,622.7,null,null],["nvidia-geforce-rtx-5060","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,"5",null],["nvidia-geforce-rtx-5060","qwen3-5-2b","cuda","fits","BF16",8192,5.38,11776,false,115.9,null,null],["nvidia-geforce-rtx-5060","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,166656,false,272.2,null,null],["nvidia-geforce-rtx-5060","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"5",null],["nvidia-geforce-rtx-5060","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-5-4b","cuda","fits","Q6_K",8192,5.43,8192,false,118.4,null,null],["nvidia-geforce-rtx-5060","qwen3-5-4b-base","cuda","fits","Q6_K",8192,5.37,9984,false,120.4,null,null],["nvidia-geforce-rtx-5060","qwen3-5-9b","cuda","tight","Q8_0",8192,10.25,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-5-9b-base","cuda","fits","Q2_K",8192,5.4,9216,false,119.4,null,null],["nvidia-geforce-rtx-5060","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"5",null],["nvidia-geforce-rtx-5060","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-8-27b","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-8-3-6-27b-blend","cuda","tight","IQ2_XXS",8192,10.58,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"6",null],["nvidia-geforce-rtx-5060","qwen3-coder-reap-25b-a3b","cuda","tight","IQ2_M",8192,9.92,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-nemotron-14b-brrm","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen3-nemotron-8b-brrm","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-geforce-rtx-5060","qwen3-vl-2b-instruct","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","qwen3-vl-2b-thinking","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-5060","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"4",null],["nvidia-geforce-rtx-5060","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"4",null],["nvidia-geforce-rtx-5060","qwen3-vl-4b-instruct","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","qwen3-vl-4b-thinking","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","qwen3-vl-8b-instruct","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwen3-vl-8b-thinking","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"6",null],["nvidia-geforce-rtx-5060","riva-translate-4b-instruct-v1-1","cuda","fits","Q4_K_M",8192,5.1,8192,false,115.1,null,null],["nvidia-geforce-rtx-5060","rlvr-8b-0926","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","rnj-1-instruct","cuda","tight","Q6_K",8192,9.02,null,null,null,null,null],["nvidia-geforce-rtx-5060","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"3",null],["nvidia-geforce-rtx-5060","singguard-2b","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","smollm3-3b","cuda","fits","Q8_0",8192,5.08,13056,false,115.7,null,null],["nvidia-geforce-rtx-5060","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,22784,false,143.3,null,null],["nvidia-geforce-rtx-5060","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","spatial-ssrl-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","spatial-ssrl-qwen3vl-4b","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-geforce-rtx-5060","step3-vl-10b-base","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","tiny-aya-earth","cuda","fits","Q4_K_M",8192,4.24,43264,false,178.5,null,null],["nvidia-geforce-rtx-5060","tiny-aya-fire","cuda","fits","Q4_K_M",8192,4.24,43264,false,178.5,null,null],["nvidia-geforce-rtx-5060","tiny-aya-global","cuda","fits","Q4_K_M",8192,4.24,43264,false,178.5,null,null],["nvidia-geforce-rtx-5060","tiny-aya-water","cuda","fits","Q4_K_M",8192,4.24,43264,false,178.5,null,null],["nvidia-geforce-rtx-5060","translategemma-12b-it","cuda","tight","Q4_K_M",8192,10.71,null,null,null,null,null],["nvidia-geforce-rtx-5060","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,"4",null],["nvidia-geforce-rtx-5060","translategemma-4b-it","cuda","fits","Q6_K",8192,5.37,11008,false,129,null,null],["nvidia-geforce-rtx-5060","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-geforce-rtx-5060","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060","trinity-mini","cuda","tight","IQ2_M",8192,10.1,null,null,null,null,null],["nvidia-geforce-rtx-5060","trinity-mini-base","cuda","tight","IQ2_M",8192,10.28,null,null,null,null,null],["nvidia-geforce-rtx-5060","trinity-mini-base-pre-anneal","cuda","tight","IQ2_M",4096,10,null,null,null,null,null],["nvidia-geforce-rtx-5060","trinity-nano-base","cuda","fits","Q4_0",8192,5.24,18688,false,601.1,null,null],["nvidia-geforce-rtx-5060","trinity-nano-base-pre-anneal","cuda","fits","Q4_K_M",4096,5.21,4096,false,635.6,null,null],["nvidia-geforce-rtx-5060","trinity-nano-preview","cuda","fits","Q4_0",8192,5.31,14848,false,583.1,null,null],["nvidia-geforce-rtx-5060","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,"3",null],["nvidia-geforce-rtx-5060","ui-mate-9b","cuda","fits","IQ2_M",8192,5.24,13824,false,124.8,null,null],["nvidia-geforce-rtx-5060","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,"4",null],["nvidia-geforce-rtx-5060","ui-venus-1-5-2b","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,"3",null],["nvidia-geforce-rtx-5060","ui-venus-1-5-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060","ui-venus-2-9b","cuda","fits","IQ2_M",8192,5.24,13824,false,124.8,null,null],["nvidia-geforce-rtx-5060","userrepgen-4b","cuda","fits","Q5_K_M",8192,5.2,14848,false,126.2,null,null],["nvidia-geforce-rtx-5060","webworld-14b","cuda","tight","IQ4_XS",8192,10.18,null,null,null,null,null],["nvidia-geforce-rtx-5060","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,"3",null],["nvidia-geforce-rtx-5060","webworld-8b","cuda","tight","Q6_K",8192,8.59,null,null,null,null,null],["nvidia-geforce-rtx-5060","x-reasoner-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,67840,false,233.4,null,null],["nvidia-geforce-rtx-5060","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,67840,false,233.4,null,null],["nvidia-geforce-rtx-5060","youtu-vl-4b-instruct","cuda","fits","Q5_K_M",8192,5.42,8448,false,114.5,null,null],["nvidia-geforce-rtx-5060","zwz-2b","cuda","fits","Q8_0",8192,4.04,20224,false,161.8,null,null],["nvidia-geforce-rtx-5060","zwz-4b","cuda","fits","Q5_K_M",8192,5.33,8704,false,109.5,null,null],["nvidia-geforce-rtx-5060","zwz-7b","cuda","fits","Q3_K_M",8192,5.28,10752,false,110.9,null,null],["nvidia-geforce-rtx-5060","zwz-8b","cuda","fits","IQ2_M",8192,5.23,9472,false,112.4,null,null],["nvidia-geforce-rtx-5060-ti-16gb","aescode-32b","cuda","tight","Q3_K_M",8192,19.28,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","aescode-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,56832,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ai21-jamba2-mini","cuda","tight","Q2_K",8192,19.01,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,10240,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","aprielguard","cuda","fits","Q6_K",8192,7.87,58880,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","armorocr","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","astabrief-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,57344,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5060-ti-16gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,13312,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,24320,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"7",null],["nvidia-geforce-rtx-5060-ti-16gb","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,9472,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","contextpilot-e4b","cuda","fits","F16",8192,10.89,118016,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,28928,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,9216,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","devstral-small-2-24b-instruct-2512","cuda","fits","Q2_K",8192,11.09,18944,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","eurollm-22b-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","eurollm-22b-instruct-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,15360,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","fara-7b","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","fara1-5-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","fara1-5-4b","cuda","fits","BF16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,84224,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,11264,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","frognano-4b-2609","cuda","fits","BF16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-2-27b-it","cuda","tight","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-3-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,15360,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-26b-a4b","cuda","tight","Q4_K_M",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-26b-a4b-it","cuda","fits","IQ2_XXS",8192,12.09,43520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-e4b","cuda","fits","F16",8192,11,111872,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","gemma-4-e4b-it","cuda","fits","BF16",8192,11,111872,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,57344,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,9984,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,11776,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"7",null],["nvidia-geforce-rtx-5060-ti-16gb","gpt-oss-20b","cuda","fits","Q6_K",8192,12.83,9728,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,18944,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-0-1b","cuda","fits","BF16",8192,5.14,102144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-1-3b","cuda","fits","BF16",8192,8.61,59904,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-2-3b","cuda","fits","BF16",8192,8.61,59904,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,17664,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,18944,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,107776,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,59904,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","hermes-4-3-36b","cuda","tight","IQ3_XXS",8192,16.93,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo-3-1-4b","cuda","fits","F16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,84736,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5060-ti-16gb","holo2-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo2-4b","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo4-27b","cuda","fits","Q2_K",8192,12.74,10240,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,48640,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,28928,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,28928,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,28928,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,28928,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","ising-calibration-1-35b-a3b","cuda","fits","IQ2_XXS",8192,11.07,89600,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","januscoder-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","kat-coder-v2-5-dev","cuda","fits","IQ2_XXS",8192,11.35,77056,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-linear-48b-a3b-instruct","cuda","tight","Q2_K",8192,18.65,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,14848,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","laguna-xs-2-1","cuda","fits","IQ2_XXS",8192,11.07,50944,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,46336,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","mathform-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,57600,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,57600,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,50688,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,57600,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,50688,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,57600,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,40448,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,84224,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,221696,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,45824,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,45824,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,23808,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,23808,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,14080,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q2_K",8192,11.09,18944,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,24576,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","north-mini-code-1-0","cuda","fits","IQ2_M",8192,12.7,9728,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"7",null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,237312,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,8448,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,12032,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,12032,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,8448,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,8448,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,11520,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","optimind-sft","cuda","tight","Q5_K_M",8192,17.77,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,19712,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","phi-4","cuda","fits","Q5_K_M",8192,12.78,8448,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,30208,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,9216,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,72192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-30b-a3b-instruct-2507","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-35b-a3b-base","cuda","fits","IQ2_XXS",8192,10.92,96512,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-4b","cuda","fits","BF16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,84736,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,84736,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-6-35b-a3b","cuda","fits","IQ2_XXS",8192,11.35,77056,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-8-27b","cuda","fits","Q2_K",8192,12.48,14080,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-8-3-6-27b-blend","cuda","fits","Q2_K",8192,12.48,14080,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-reap-25b-a3b","cuda","fits","IQ3_XXS",8192,11.77,19200,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-5060-ti-16gb","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,22528,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","singguard-2b","cuda","fits","F16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,100864,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"5",null],["nvidia-geforce-rtx-5060-ti-16gb","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-5060-ti-16gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-5060-ti-16gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8",null],["nvidia-geforce-rtx-5060-ti-16gb","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","tiny-aya-earth","cuda","fits","BF16",8192,8.72,190720,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","tiny-aya-fire","cuda","fits","BF16",8192,8.72,190720,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","tiny-aya-global","cuda","fits","BF16",8192,8.72,190720,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","tiny-aya-water","cuda","fits","BF16",8192,8.72,190720,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","translategemma-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-mini","cuda","fits","IQ3_XXS",8192,12.12,48640,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,68096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-mini-base-pre-anneal","cuda","fits","IQ3_XXS",4096,11.48,4096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-mate-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,84224,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,10240,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-venus-1-5-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,84224,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","userrepgen-4b","cuda","fits","BF16",8192,10.23,85504,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","webworld-8b","cuda","fits","Q8_0",8192,10.39,25088,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,100864,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","zwz-2b","cuda","fits","F16",8192,5.62,71424,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","zwz-4b","cuda","fits","Q6_K",8192,5.74,56832,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","zwz-7b","cuda","fits","Q6_K",8192,7.47,100864,false,null,null,null],["nvidia-geforce-rtx-5060-ti-16gb","zwz-8b","cuda","fits","Q6_K",8192,8.59,37376,false,null,null,null],["nvidia-geforce-rtx-5070","aescode-32b","cuda","tight","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-geforce-rtx-5070","aescode-8b","cuda","fits","Q5_K_M",8192,8.2,12544,false,95.8,null,null],["nvidia-geforce-rtx-5070","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,29440,false,149.1,null,null],["nvidia-geforce-rtx-5070","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,110.6,null,null],["nvidia-geforce-rtx-5070","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,110.6,null,null],["nvidia-geforce-rtx-5070","ai21-jamba2-mini","cuda","tight","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-geforce-rtx-5070","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,256.7,null,null],["nvidia-geforce-rtx-5070","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,256.7,null,null],["nvidia-geforce-rtx-5070","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,209.3,null,null],["nvidia-geforce-rtx-5070","apriel-1-6-15b-thinker","cuda","fits","IQ3_XXS",8192,8.24,11264,false,94.7,null,null],["nvidia-geforce-rtx-5070","aprielguard","cuda","fits","Q6_K",8192,7.87,18176,false,99.9,null,null],["nvidia-geforce-rtx-5070","armorocr","cuda","fits","Q4_K_M",8192,7.09,20224,false,114.3,null,null],["nvidia-geforce-rtx-5070","astabrief-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","autoglm-phone-9b","cuda","fits","Q5_K_M",8192,8.13,25600,false,96.7,null,null],["nvidia-geforce-rtx-5070","autoglm-phone-9b-multilingual","cuda","fits","Q5_K_M",8192,8.13,25600,false,96.7,null,null],["nvidia-geforce-rtx-5070","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5070","bielik-11b-v3-0-instruct","cuda","tight","Q8_0",8192,14.42,null,null,null,null,null],["nvidia-geforce-rtx-5070","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q6_K",8192,8.5,10240,false,91.2,null,null],["nvidia-geforce-rtx-5070","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,218.7,null,null],["nvidia-geforce-rtx-5070","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","caprl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-5070","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","contextpilot-14b","cuda","fits","IQ3_XXS",8192,8.43,10752,false,92.7,null,null],["nvidia-geforce-rtx-5070","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","contextpilot-e4b","cuda","fits","Q8_0",8192,6.65,131072,false,131.3,null,null],["nvidia-geforce-rtx-5070","cosmos-reason2-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-5070","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,121.5,null,null],["nvidia-geforce-rtx-5070","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-5070","deepseek-r1-0528-qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-5070","deepseek-r1-distill-llama-8b","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","deepseek-r1-distill-qwen-14b","cuda","fits","Q2_K",8192,8.3,11008,false,94.4,null,null],["nvidia-geforce-rtx-5070","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-5070","deepseek-r1-distill-qwen-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-5070","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-5070","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-5070","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-5070","devstral-small-2-24b-instruct-2512","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-5070","eurollm-22b-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-5070","eurollm-22b-instruct-2512","cuda","tight","IQ4_XS",8192,14.71,null,null,null,null,null],["nvidia-geforce-rtx-5070","eurollm-9b-instruct-2512","cuda","fits","Q5_K_M",8192,8.69,9216,false,88.8,null,null],["nvidia-geforce-rtx-5070","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1093.3,null,null],["nvidia-geforce-rtx-5070","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"3",null],["nvidia-geforce-rtx-5070","fara-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","fara1-5-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-5070","fara1-5-4b","cuda","fits","Q8_0",8192,6.38,81152,false,141.4,null,null],["nvidia-geforce-rtx-5070","fara1-5-9b","cuda","fits","Q6_K",8192,8.7,13056,false,94.3,null,null],["nvidia-geforce-rtx-5070","frogboss-32b-2510","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-5070","frogmini-14b-2510","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","frognano-4b-2609","cuda","fits","Q8_0",8192,6.38,81152,false,141.4,null,null],["nvidia-geforce-rtx-5070","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1180.3,null,null],["nvidia-geforce-rtx-5070","gelab-zero-4b-preview","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","gemma-2-27b-it","cuda","tight","IQ3_XXS",8192,15.11,null,null,null,null,null],["nvidia-geforce-rtx-5070","gemma-2-9b-it","cuda","fits","IQ3_XXS",8192,8.03,8192,false,113.8,null,null],["nvidia-geforce-rtx-5070","gemma-3-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,119.3,null,null],["nvidia-geforce-rtx-5070","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,328.6,null,null],["nvidia-geforce-rtx-5070","gemma-3-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-5070","gemma-3-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,152.3,null,null],["nvidia-geforce-rtx-5070","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-5070","gemma-4-12b-it","cuda","fits","Q3_K_M",8192,8.73,16128,false,109.3,null,null],["nvidia-geforce-rtx-5070","gemma-4-26b-a4b","cuda","tight","Q2_K",8192,13,null,null,null,null,null],["nvidia-geforce-rtx-5070","gemma-4-26b-a4b-it","cuda","tight","Q3_K_M",8192,15.39,null,null,null,null,null],["nvidia-geforce-rtx-5070","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,"3",null],["nvidia-geforce-rtx-5070","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,"3",null],["nvidia-geforce-rtx-5070","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,343,null,null],["nvidia-geforce-rtx-5070","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,144.4,null,null],["nvidia-geforce-rtx-5070","gemma-4-e4b","cuda","fits","Q8_0",8192,6.7,128256,false,129.8,null,null],["nvidia-geforce-rtx-5070","gemma-4-e4b-it","cuda","fits","Q8_0",8192,6.86,119296,false,125.9,null,null],["nvidia-geforce-rtx-5070","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-5070","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"5",null],["nvidia-geforce-rtx-5070","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"7",null],["nvidia-geforce-rtx-5070","glm-4-6v-flash","cuda","fits","Q5_K_M",8192,8.13,25600,false,96.7,null,null],["nvidia-geforce-rtx-5070","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-4-7-flash","cuda","tight","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-geforce-rtx-5070","glm-4-7-flash-reap-23b-a3b","cuda","tight","Q4_0",8192,14.61,null,null,null,null,null],["nvidia-geforce-rtx-5070","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5070","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","gpt-oss-20b","cuda","tight","Q8_0",8192,12.9,null,null,null,null,null],["nvidia-geforce-rtx-5070","granite-3-3-8b-instruct","cuda","fits","Q5_K_M",8192,8.28,11776,false,94.1,null,null],["nvidia-geforce-rtx-5070","granite-4-0-1b","cuda","fits","BF16",8192,5.14,53504,false,170.8,null,null],["nvidia-geforce-rtx-5070","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,715.1,null,null],["nvidia-geforce-rtx-5070","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,224.6,null,null],["nvidia-geforce-rtx-5070","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,940,null,null],["nvidia-geforce-rtx-5070","granite-4-1-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-5070","granite-4-1-3b","cuda","fits","BF16",8192,8.61,11264,false,89.9,null,null],["nvidia-geforce-rtx-5070","granite-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,91.9,null,null],["nvidia-geforce-rtx-5070","granite-4-2-30b","cuda","tight","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-5070","granite-4-2-3b","cuda","fits","BF16",8192,8.61,11264,false,89.9,null,null],["nvidia-geforce-rtx-5070","granite-4-2-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,91.9,null,null],["nvidia-geforce-rtx-5070","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q5_K_M",8192,8.28,11776,false,94.1,null,null],["nvidia-geforce-rtx-5070","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,59136,false,194,null,null],["nvidia-geforce-rtx-5070","granite-guardian-4-1-8b","cuda","fits","Q5_K_M",8192,8.45,10752,false,91.9,null,null],["nvidia-geforce-rtx-5070","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,11264,false,89.9,null,null],["nvidia-geforce-rtx-5070","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","hermes-4-3-36b","cuda","tight","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-geforce-rtx-5070","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,285.8,null,null],["nvidia-geforce-rtx-5070","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,934.1,null,null],["nvidia-geforce-rtx-5070","holo-3-1-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-5070","holo-3-1-4b","cuda","fits","Q8_0",8192,6.37,81408,false,141.8,null,null],["nvidia-geforce-rtx-5070","holo-3-1-9b","cuda","fits","Q6_K",8192,8.37,22784,false,99.1,null,null],["nvidia-geforce-rtx-5070","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","holo2-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-5070","holo2-4b","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","holo2-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","holo3-35b-a3b","cuda","tight","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-geforce-rtx-5070","holo4-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-5070","holo4-35b-a3b","cuda","tight","Q2_K",8192,14.96,null,null,null,null,null],["nvidia-geforce-rtx-5070","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-5070","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,356.8,null,null],["nvidia-geforce-rtx-5070","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"6",null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-geforce-rtx-5070","ising-calibration-1-35b-a3b","cuda","tight","IQ3_XXS",8192,15.07,null,null,null,null,null],["nvidia-geforce-rtx-5070","ising-calibration-1-5-31b-bf16","cuda","tight","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-geforce-rtx-5070","januscoder-14b","cuda","fits","Q2_K",8192,8.02,13312,false,98.3,null,null],["nvidia-geforce-rtx-5070","januscoder-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","januscoderv-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-geforce-rtx-5070","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,182.4,null,null],["nvidia-geforce-rtx-5070","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,10496,false,90.4,null,null],["nvidia-geforce-rtx-5070","kat-coder-v2-5-dev","cuda","tight","Q2_K",8192,14.13,null,null,null,null,null],["nvidia-geforce-rtx-5070","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"4",null],["nvidia-geforce-rtx-5070","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5070","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-5070","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5070","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5070","kimi-linear-48b-a3b-base","cuda","tight","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-geforce-rtx-5070","kimi-linear-48b-a3b-instruct","cuda","tight","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-geforce-rtx-5070","kimi-linear-reap-35b-a3b-instruct","cuda","tight","IQ3_XXS",8192,14.77,null,null,null,null,null],["nvidia-geforce-rtx-5070","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","laguna-xs-2-1","cuda","tight","Q2_K",8192,13.77,null,null,null,null,null],["nvidia-geforce-rtx-5070","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-5070","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-5070","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-5070","lfm2-24b-a2b","cuda","tight","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-geforce-rtx-5070","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,128256,false,121.5,null,null],["nvidia-geforce-rtx-5070","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,286.3,null,null],["nvidia-geforce-rtx-5070","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1199.7,null,null],["nvidia-geforce-rtx-5070","lfm2-5-24b-a2b","cuda","tight","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-5070","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-5070","lfm2-5-8b-a1b","cuda","fits","Q6_K",8192,8.19,56576,false,451.4,null,null],["nvidia-geforce-rtx-5070","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,1715.8,null,null],["nvidia-geforce-rtx-5070","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,275.2,null,null],["nvidia-geforce-rtx-5070","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,121.5,null,null],["nvidia-geforce-rtx-5070","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-5070","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,829.9,null,null],["nvidia-geforce-rtx-5070","lfm2-8b-a1b","cuda","fits","Q6_K",8192,8.09,63744,false,485.6,null,null],["nvidia-geforce-rtx-5070","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,127.4,null,null],["nvidia-geforce-rtx-5070","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5070","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"3",null],["nvidia-geforce-rtx-5070","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,12032,false,92.9,null,null],["nvidia-geforce-rtx-5070","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,245.2,null,null],["nvidia-geforce-rtx-5070","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,11264,false,91.2,null,null],["nvidia-geforce-rtx-5070","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"4",null],["nvidia-geforce-rtx-5070","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"6",null],["nvidia-geforce-rtx-5070","mathform-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","medgemma-1-5-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,152.3,null,null],["nvidia-geforce-rtx-5070","mellum2-1-12b-a2-5b-thinking","cuda","tight","Q8_0",8192,14.03,null,null,null,null,null],["nvidia-geforce-rtx-5070","mellum2-12b-a2-5b-base","cuda","fits","Q4_0",8192,8.27,45824,false,453.4,null,null],["nvidia-geforce-rtx-5070","mellum2-12b-a2-5b-instruct","cuda","fits","Q4_0",8192,8.34,41728,false,433.7,null,null],["nvidia-geforce-rtx-5070","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q4_0",8192,8.27,45824,false,453.4,null,null],["nvidia-geforce-rtx-5070","mellum2-12b-a2-5b-thinking","cuda","fits","Q4_0",8192,8.34,41728,false,433.7,null,null],["nvidia-geforce-rtx-5070","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q4_0",8192,8.27,45824,false,453.4,null,null],["nvidia-geforce-rtx-5070","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,13056,false,96.7,null,null],["nvidia-geforce-rtx-5070","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mimo-v2-6-distill-qwen-9b","cuda","fits","Q6_K",8192,8.8,10240,false,93.1,null,null],["nvidia-geforce-rtx-5070","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-geforce-rtx-5070","minicpm-o-4-5","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-5070","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-5070","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,418.4,null,null],["nvidia-geforce-rtx-5070","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"3",null],["nvidia-geforce-rtx-5070","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-5070","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-5070","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,727.7,null,null],["nvidia-geforce-rtx-5070","minicpm5-2b","cuda","fits","BF16",8192,6.04,72448,false,138.5,null,null],["nvidia-geforce-rtx-5070","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,131328,false,305.7,null,null],["nvidia-geforce-rtx-5070","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"6",null],["nvidia-geforce-rtx-5070","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","ministral-3-14b-instruct-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-5070","ministral-3-14b-reasoning-2512","cuda","tight","Q5_K_M",8192,11.57,null,null,null,null,null],["nvidia-geforce-rtx-5070","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,8192,false,86.9,null,null],["nvidia-geforce-rtx-5070","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,8192,false,86.9,null,null],["nvidia-geforce-rtx-5070","ministral-3-8b-instruct-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,98.5,null,null],["nvidia-geforce-rtx-5070","ministral-3-8b-reasoning-2512","cuda","fits","Q5_K_M",8192,7.97,14592,false,98.5,null,null],["nvidia-geforce-rtx-5070","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,14336,false,97.3,null,null],["nvidia-geforce-rtx-5070","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-5070","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"7",null],["nvidia-geforce-rtx-5070","mistral-nemo-instruct-2407","cuda","fits","IQ4_XS",8192,8.85,8192,false,87,null,null],["nvidia-geforce-rtx-5070","mistral-small-3-2-24b-instruct-2506","cuda","tight","IQ4_XS",8192,14.75,null,null,null,null,null],["nvidia-geforce-rtx-5070","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"7",null],["nvidia-geforce-rtx-5070","muse-glimmer-30b","cuda","tight","Q3_K_M",8192,14.97,null,null,null,null,null],["nvidia-geforce-rtx-5070","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5070","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,193.5,null,null],["nvidia-geforce-rtx-5070","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"4",null],["nvidia-geforce-rtx-5070","nemotron-cascade-14b-thinking","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-5070","nemotron-cascade-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","nemotron-cascade-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","nemotron-orchestrator-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","nemotron-terminal-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","nemotron-terminal-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-5070","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","north-mini-code-1-0","cuda","tight","IQ3_XXS",8192,15.09,null,null,null,null,null],["nvidia-geforce-rtx-5070","nouscoder-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,"3",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,"3",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,15872,false,92.5,null,null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"7",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"7",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,"3",null],["nvidia-geforce-rtx-5070","nvidia-nemotron-nano-9b-v2","cuda","fits","Q5_K_M",8192,8.47,30208,false,99.5,null,null],["nvidia-geforce-rtx-5070","olmo-3-1-32b-instruct","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-1-32b-instruct-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-1-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-1-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-1-7b-rl-zero-math","cuda","fits","Q2_K",8192,8.17,9472,false,124.4,null,null],["nvidia-geforce-rtx-5070","olmo-3-1125-32b","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-32b-think","cuda","tight","Q2_K",8192,15,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-32b-think-dpo","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-32b-think-sft","cuda","tight","IQ3_XXS",8192,15.48,null,null,null,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-instruct","cuda","fits","Q2_K",8192,8.17,9472,false,124.4,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-instruct-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-instruct-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-rl-zero-code","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-rl-zero-general","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-rl-zero-if","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-rl-zero-math","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-rl-zero-mix","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-think","cuda","fits","Q2_K",8192,8.17,9472,false,124.4,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-think-dpo","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmo-3-7b-think-sft","cuda","fits","IQ3_XXS",8192,8.17,9472,false,124.3,null,null],["nvidia-geforce-rtx-5070","olmocr-2-7b-1025","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","optimind-sft","cuda","tight","Q4_0",8192,13.22,null,null,null,null,null],["nvidia-geforce-rtx-5070","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,9472,false,93.6,null,null],["nvidia-geforce-rtx-5070","phi-4","cuda","fits","Q2_K",8192,8.25,11008,false,94.5,null,null],["nvidia-geforce-rtx-5070","phi-4-mini-instruct","cuda","fits","Q8_0",8192,6.47,26624,false,130.5,null,null],["nvidia-geforce-rtx-5070","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"6",null],["nvidia-geforce-rtx-5070","qwen2-5-14b-instruct","cuda","fits","Q2_K",8192,8.3,11008,false,94.4,null,null],["nvidia-geforce-rtx-5070","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-5070","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,187.6,null,null],["nvidia-geforce-rtx-5070","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"5",null],["nvidia-geforce-rtx-5070","qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,"2",null],["nvidia-geforce-rtx-5070","qwen2-5-coder-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","qwen2-5-vl-7b-instruct","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,315.2,null,null],["nvidia-geforce-rtx-5070","qwen3-1-7b","cuda","fits","BF16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","qwen3-14b","cuda","tight","Q6_K",8192,13.89,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-geforce-rtx-5070","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"3",null],["nvidia-geforce-rtx-5070","qwen3-30b-a3b-instruct-2507","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"3",null],["nvidia-geforce-rtx-5070","qwen3-4b","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","qwen3-4b-instruct-2507","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,418.3,null,null],["nvidia-geforce-rtx-5070","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,934.1,null,null],["nvidia-geforce-rtx-5070","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"6",null],["nvidia-geforce-rtx-5070","qwen3-5-27b","cuda","tight","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-5-2b","cuda","fits","BF16",8192,5.38,256512,false,173.8,null,null],["nvidia-geforce-rtx-5070","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,408.2,null,null],["nvidia-geforce-rtx-5070","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,"3",null],["nvidia-geforce-rtx-5070","qwen3-5-35b-a3b-base","cuda","tight","IQ3_XXS",8192,14.98,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-5070","qwen3-5-4b","cuda","fits","Q8_0",8192,6.37,81408,false,141.8,null,null],["nvidia-geforce-rtx-5070","qwen3-5-4b-base","cuda","fits","Q8_0",8192,6.37,81408,false,141.8,null,null],["nvidia-geforce-rtx-5070","qwen3-5-9b","cuda","fits","Q6_K",8192,8.47,19968,false,97.7,null,null],["nvidia-geforce-rtx-5070","qwen3-5-9b-base","cuda","fits","Q6_K",8192,8.37,22784,false,99.1,null,null],["nvidia-geforce-rtx-5070","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,"2",null],["nvidia-geforce-rtx-5070","qwen3-6-35b-a3b","cuda","tight","Q2_K",8192,14.12,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5070","qwen3-8-27b","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-8-3-6-27b-blend","cuda","tight","Q3_K_M",8192,14.85,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","qwen3-coder-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-5070","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"5",null],["nvidia-geforce-rtx-5070","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"3",null],["nvidia-geforce-rtx-5070","qwen3-coder-reap-25b-a3b","cuda","fits","IQ2_XXS",8192,8.11,15872,false,358.8,null,null],["nvidia-geforce-rtx-5070","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-geforce-rtx-5070","qwen3-nemotron-14b-brrm","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"5",null],["nvidia-geforce-rtx-5070","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-30b-a3b-instruct","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-5070","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,"2",null],["nvidia-geforce-rtx-5070","qwen3-vl-4b-instruct","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-4b-thinking","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-8b-instruct","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","qwen3-vl-8b-thinking","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"3",null],["nvidia-geforce-rtx-5070","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,140.3,null,null],["nvidia-geforce-rtx-5070","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","rnj-1-instruct","cuda","fits","Q5_K_M",8192,8.15,13568,false,95.9,null,null],["nvidia-geforce-rtx-5070","sera-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-5070","singguard-2b","cuda","fits","F16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","smollm3-3b","cuda","fits","BF16",8192,7.9,21248,false,99.5,null,null],["nvidia-geforce-rtx-5070","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,214.9,null,null],["nvidia-geforce-rtx-5070","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"5",null],["nvidia-geforce-rtx-5070","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","spatial-ssrl-qwen3vl-4b","cuda","fits","Q8_0",8192,6.7,23040,false,122.6,null,null],["nvidia-geforce-rtx-5070","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"8",null],["nvidia-geforce-rtx-5070","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"5",null],["nvidia-geforce-rtx-5070","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"6",null],["nvidia-geforce-rtx-5070","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","tiny-aya-earth","cuda","fits","BF16",8192,8.72,10240,false,95,null,null],["nvidia-geforce-rtx-5070","tiny-aya-fire","cuda","fits","BF16",8192,8.72,10240,false,95,null,null],["nvidia-geforce-rtx-5070","tiny-aya-global","cuda","fits","BF16",8192,8.72,10240,false,95,null,null],["nvidia-geforce-rtx-5070","tiny-aya-water","cuda","fits","BF16",8192,8.72,10240,false,95,null,null],["nvidia-geforce-rtx-5070","translategemma-12b-it","cuda","fits","Q2_K",8192,8.23,17920,false,119.3,null,null],["nvidia-geforce-rtx-5070","translategemma-27b-it","cuda","tight","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-geforce-rtx-5070","translategemma-4b-it","cuda","fits","Q8_0",8192,6.3,124928,false,152.3,null,null],["nvidia-geforce-rtx-5070","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070","trinity-mini","cuda","fits","IQ2_XXS",8192,8.25,41216,false,488.7,null,null],["nvidia-geforce-rtx-5070","trinity-mini-base","cuda","fits","IQ2_XXS",8192,8.69,16640,false,539.8,null,null],["nvidia-geforce-rtx-5070","trinity-mini-base-pre-anneal","cuda","fits","IQ2_XXS",4096,8.41,4096,false,570.5,null,null],["nvidia-geforce-rtx-5070","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,746.2,null,null],["nvidia-geforce-rtx-5070","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,798.2,null,null],["nvidia-geforce-rtx-5070","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,56320,false,612.5,null,null],["nvidia-geforce-rtx-5070","ui-mate-27b","cuda","tight","IQ3_XXS",8192,14.25,null,null,null,null,null],["nvidia-geforce-rtx-5070","ui-mate-9b","cuda","fits","Q6_K",8192,8.7,13056,false,94.3,null,null],["nvidia-geforce-rtx-5070","ui-mate-democua-27b","cuda","tight","Q3_K_M",8192,15.15,null,null,null,null,null],["nvidia-geforce-rtx-5070","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","ui-venus-1-5-30b-a3b","cuda","tight","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-geforce-rtx-5070","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","ui-venus-2-9b","cuda","fits","Q6_K",8192,8.7,13056,false,94.3,null,null],["nvidia-geforce-rtx-5070","userrepgen-4b","cuda","fits","Q8_0",8192,6.38,81152,false,141.4,null,null],["nvidia-geforce-rtx-5070","webworld-14b","cuda","fits","IQ3_XXS",8192,8.13,12544,false,96.8,null,null],["nvidia-geforce-rtx-5070","webworld-32b","cuda","tight","IQ2_M",8192,14.23,null,null,null,null,null],["nvidia-geforce-rtx-5070","webworld-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,350,null,null],["nvidia-geforce-rtx-5070","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,350,null,null],["nvidia-geforce-rtx-5070","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,152.2,null,null],["nvidia-geforce-rtx-5070","zwz-2b","cuda","fits","F16",8192,5.62,36608,false,153.4,null,null],["nvidia-geforce-rtx-5070","zwz-4b","cuda","fits","Q6_K",8192,5.74,29440,false,149.1,null,null],["nvidia-geforce-rtx-5070","zwz-7b","cuda","fits","Q6_K",8192,7.47,32256,false,107.2,null,null],["nvidia-geforce-rtx-5070","zwz-8b","cuda","fits","Q6_K",8192,8.59,9984,false,90.6,null,null],["nvidia-geforce-rtx-5070-ti","aescode-32b","cuda","tight","Q3_K_M",8192,19.28,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","aescode-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,56832,false,198.7,null,null],["nvidia-geforce-rtx-5070-ti","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,147.5,null,null],["nvidia-geforce-rtx-5070-ti","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,147.5,null,null],["nvidia-geforce-rtx-5070-ti","ai21-jamba2-mini","cuda","tight","Q2_K",8192,19.01,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,342.3,null,null],["nvidia-geforce-rtx-5070-ti","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,342.3,null,null],["nvidia-geforce-rtx-5070-ti","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,279.1,null,null],["nvidia-geforce-rtx-5070-ti","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,10240,false,78.5,null,null],["nvidia-geforce-rtx-5070-ti","aprielguard","cuda","fits","Q6_K",8192,7.87,58880,false,133.2,null,null],["nvidia-geforce-rtx-5070-ti","armorocr","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","astabrief-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,57344,false,92.7,null,null],["nvidia-geforce-rtx-5070-ti","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,110.8,null,null],["nvidia-geforce-rtx-5070-ti","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5070-ti","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,13312,false,83.5,null,null],["nvidia-geforce-rtx-5070-ti","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,24320,false,97.9,null,null],["nvidia-geforce-rtx-5070-ti","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,291.6,null,null],["nvidia-geforce-rtx-5070-ti","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"7",null],["nvidia-geforce-rtx-5070-ti","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,9472,false,77.6,null,null],["nvidia-geforce-rtx-5070-ti","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","contextpilot-e4b","cuda","fits","F16",8192,10.89,118016,false,94.9,null,null],["nvidia-geforce-rtx-5070-ti","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,82.2,null,null],["nvidia-geforce-rtx-5070-ti","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,162.1,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,28928,false,99,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,9216,false,77.4,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","devstral-small-2-24b-instruct-2512","cuda","fits","Q2_K",8192,11.09,18944,false,89.6,null,null],["nvidia-geforce-rtx-5070-ti","eurollm-22b-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,85.9,null,null],["nvidia-geforce-rtx-5070-ti","eurollm-22b-instruct-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,85.9,null,null],["nvidia-geforce-rtx-5070-ti","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,15360,false,84.7,null,null],["nvidia-geforce-rtx-5070-ti","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1457.7,null,null],["nvidia-geforce-rtx-5070-ti","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","fara-7b","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","fara1-5-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,84.4,null,null],["nvidia-geforce-rtx-5070-ti","fara1-5-4b","cuda","fits","BF16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,84224,false,102.7,null,null],["nvidia-geforce-rtx-5070-ti","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,11264,false,82.2,null,null],["nvidia-geforce-rtx-5070-ti","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","frognano-4b-2609","cuda","fits","BF16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1573.8,null,null],["nvidia-geforce-rtx-5070-ti","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","gemma-2-27b-it","cuda","tight","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,90.3,null,null],["nvidia-geforce-rtx-5070-ti","gemma-3-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,96.2,null,null],["nvidia-geforce-rtx-5070-ti","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,438.1,null,null],["nvidia-geforce-rtx-5070-ti","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,111.3,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,15360,false,87.5,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-26b-a4b","cuda","tight","Q4_K_M",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-26b-a4b-it","cuda","fits","IQ2_XXS",8192,12.09,43520,false,391.2,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,457.3,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,192.5,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-e4b","cuda","fits","F16",8192,11,111872,false,93.8,null,null],["nvidia-geforce-rtx-5070-ti","gemma-4-e4b-it","cuda","fits","BF16",8192,11,111872,false,93.8,null,null],["nvidia-geforce-rtx-5070-ti","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,57344,false,92.7,null,null],["nvidia-geforce-rtx-5070-ti","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,9984,false,398.9,null,null],["nvidia-geforce-rtx-5070-ti","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,11776,false,358.3,null,null],["nvidia-geforce-rtx-5070-ti","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-5070-ti","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"7",null],["nvidia-geforce-rtx-5070-ti","gpt-oss-20b","cuda","fits","Q6_K",8192,12.83,9728,false,330.6,null,null],["nvidia-geforce-rtx-5070-ti","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,18944,false,89.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-0-1b","cuda","fits","BF16",8192,5.14,102144,false,227.7,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,953.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,299.5,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1253.3,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-1-3b","cuda","fits","BF16",8192,8.61,59904,false,119.8,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,87.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-2-3b","cuda","fits","BF16",8192,8.61,59904,false,119.8,null,null],["nvidia-geforce-rtx-5070-ti","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,17664,false,87.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,18944,false,89.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,107776,false,258.7,null,null],["nvidia-geforce-rtx-5070-ti","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,87.4,null,null],["nvidia-geforce-rtx-5070-ti","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,59904,false,119.8,null,null],["nvidia-geforce-rtx-5070-ti","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,123.9,null,null],["nvidia-geforce-rtx-5070-ti","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,142.9,null,null],["nvidia-geforce-rtx-5070-ti","hermes-4-3-36b","cuda","tight","IQ3_XXS",8192,16.93,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,381.1,null,null],["nvidia-geforce-rtx-5070-ti","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1245.4,null,null],["nvidia-geforce-rtx-5070-ti","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","holo-3-1-4b","cuda","fits","F16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,84736,false,102.9,null,null],["nvidia-geforce-rtx-5070-ti","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5070-ti","holo2-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","holo2-4b","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","holo2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","holo4-27b","cuda","fits","Q2_K",8192,12.74,10240,false,82.8,null,null],["nvidia-geforce-rtx-5070-ti","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,48640,false,522.7,null,null],["nvidia-geforce-rtx-5070-ti","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,475.7,null,null],["nvidia-geforce-rtx-5070-ti","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,28928,false,99,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,28928,false,99,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,28928,false,99,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,28928,false,99,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","ising-calibration-1-35b-a3b","cuda","fits","IQ2_XXS",8192,11.07,89600,false,645.8,null,null],["nvidia-geforce-rtx-5070-ti","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","januscoder-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,243.3,null,null],["nvidia-geforce-rtx-5070-ti","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,120.5,null,null],["nvidia-geforce-rtx-5070-ti","kat-coder-v2-5-dev","cuda","fits","IQ2_XXS",8192,11.35,77056,false,543,null,null],["nvidia-geforce-rtx-5070-ti","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","kimi-linear-48b-a3b-instruct","cuda","tight","Q2_K",8192,18.65,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,14848,false,674,null,null],["nvidia-geforce-rtx-5070-ti","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","laguna-xs-2-1","cuda","fits","IQ2_XXS",8192,11.07,50944,false,491.4,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,169.9,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,169.9,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,169.9,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,162.1,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,381.7,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1599.5,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,1106.5,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,472.4,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,2287.7,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,367,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,162.1,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,1106.5,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,1106.5,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,508.9,null,null],["nvidia-geforce-rtx-5070-ti","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,169.9,null,null],["nvidia-geforce-rtx-5070-ti","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,123.9,null,null],["nvidia-geforce-rtx-5070-ti","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,327,null,null],["nvidia-geforce-rtx-5070-ti","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,46336,false,121.7,null,null],["nvidia-geforce-rtx-5070-ti","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","mathform-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,111.3,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,57600,false,426.3,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,57600,false,426.3,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,50688,false,404.7,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,57600,false,426.3,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,50688,false,404.7,null,null],["nvidia-geforce-rtx-5070-ti","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,57600,false,426.3,null,null],["nvidia-geforce-rtx-5070-ti","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,40448,false,128.9,null,null],["nvidia-geforce-rtx-5070-ti","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,84224,false,102.7,null,null],["nvidia-geforce-rtx-5070-ti","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,557.9,null,null],["nvidia-geforce-rtx-5070-ti","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,557.9,null,null],["nvidia-geforce-rtx-5070-ti","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,557.9,null,null],["nvidia-geforce-rtx-5070-ti","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,970.2,null,null],["nvidia-geforce-rtx-5070-ti","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,970.2,null,null],["nvidia-geforce-rtx-5070-ti","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,970.2,null,null],["nvidia-geforce-rtx-5070-ti","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,184.7,null,null],["nvidia-geforce-rtx-5070-ti","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,221696,false,407.6,null,null],["nvidia-geforce-rtx-5070-ti","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-5070-ti","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,85.4,null,null],["nvidia-geforce-rtx-5070-ti","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,85.4,null,null],["nvidia-geforce-rtx-5070-ti","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,45824,false,115.9,null,null],["nvidia-geforce-rtx-5070-ti","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,45824,false,115.9,null,null],["nvidia-geforce-rtx-5070-ti","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,23808,false,93.4,null,null],["nvidia-geforce-rtx-5070-ti","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,23808,false,93.4,null,null],["nvidia-geforce-rtx-5070-ti","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,129.7,null,null],["nvidia-geforce-rtx-5070-ti","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,14080,false,82.7,null,null],["nvidia-geforce-rtx-5070-ti","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q2_K",8192,11.09,18944,false,89.6,null,null],["nvidia-geforce-rtx-5070-ti","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,24576,false,80.4,null,null],["nvidia-geforce-rtx-5070-ti","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,257.9,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,82.2,null,null],["nvidia-geforce-rtx-5070-ti","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","north-mini-code-1-0","cuda","fits","IQ2_M",8192,12.7,9728,false,421.4,null,null],["nvidia-geforce-rtx-5070-ti","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"7",null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,237312,false,123.4,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,100,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,90.3,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,8448,false,89.6,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,12032,false,90.3,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,90.3,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,12032,false,90.3,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,8448,false,89.6,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,8448,false,89.6,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,11520,false,107.5,null,null],["nvidia-geforce-rtx-5070-ti","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","optimind-sft","cuda","tight","Q5_K_M",8192,17.77,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,19712,false,124.8,null,null],["nvidia-geforce-rtx-5070-ti","phi-4","cuda","fits","Q5_K_M",8192,12.78,8448,false,76.4,null,null],["nvidia-geforce-rtx-5070-ti","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,30208,false,102.4,null,null],["nvidia-geforce-rtx-5070-ti","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,9216,false,77.4,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,250.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,72192,false,112.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,420.3,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","qwen3-30b-a3b-instruct-2507","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,163.4,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,557.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1245.4,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,231.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,544.3,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-35b-a3b-base","cuda","fits","IQ2_XXS",8192,10.92,96512,false,726,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","qwen3-5-4b","cuda","fits","BF16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,84736,false,102.9,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,84736,false,102.9,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-6-35b-a3b","cuda","fits","IQ2_XXS",8192,11.35,77056,false,543.1,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","qwen3-8-27b","cuda","fits","Q2_K",8192,12.48,14080,false,84.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-8-3-6-27b-blend","cuda","fits","Q2_K",8192,12.48,14080,false,84.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-reap-25b-a3b","cuda","fits","IQ3_XXS",8192,11.77,19200,false,397.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5070-ti","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-5070-ti","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,187.1,null,null],["nvidia-geforce-rtx-5070-ti","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,22528,false,90.5,null,null],["nvidia-geforce-rtx-5070-ti","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,82.2,null,null],["nvidia-geforce-rtx-5070-ti","singguard-2b","cuda","fits","F16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,132.7,null,null],["nvidia-geforce-rtx-5070-ti","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,286.5,null,null],["nvidia-geforce-rtx-5070-ti","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,100864,false,142.9,null,null],["nvidia-geforce-rtx-5070-ti","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,96.8,null,null],["nvidia-geforce-rtx-5070-ti","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"5",null],["nvidia-geforce-rtx-5070-ti","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-5070-ti","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-5070-ti","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8",null],["nvidia-geforce-rtx-5070-ti","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","tiny-aya-earth","cuda","fits","BF16",8192,8.72,190720,false,126.6,null,null],["nvidia-geforce-rtx-5070-ti","tiny-aya-fire","cuda","fits","BF16",8192,8.72,190720,false,126.6,null,null],["nvidia-geforce-rtx-5070-ti","tiny-aya-global","cuda","fits","BF16",8192,8.72,190720,false,126.6,null,null],["nvidia-geforce-rtx-5070-ti","tiny-aya-water","cuda","fits","BF16",8192,8.72,190720,false,126.6,null,null],["nvidia-geforce-rtx-5070-ti","translategemma-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,96.2,null,null],["nvidia-geforce-rtx-5070-ti","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,111.3,null,null],["nvidia-geforce-rtx-5070-ti","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5070-ti","trinity-mini","cuda","fits","IQ3_XXS",8192,12.12,48640,false,509.7,null,null],["nvidia-geforce-rtx-5070-ti","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,68096,false,573.5,null,null],["nvidia-geforce-rtx-5070-ti","trinity-mini-base-pre-anneal","cuda","fits","IQ3_XXS",4096,11.48,4096,false,599.3,null,null],["nvidia-geforce-rtx-5070-ti","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,994.9,null,null],["nvidia-geforce-rtx-5070-ti","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,1064.3,null,null],["nvidia-geforce-rtx-5070-ti","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,131072,false,816.7,null,null],["nvidia-geforce-rtx-5070-ti","ui-mate-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,84.4,null,null],["nvidia-geforce-rtx-5070-ti","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,84224,false,102.7,null,null],["nvidia-geforce-rtx-5070-ti","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,10240,false,82.8,null,null],["nvidia-geforce-rtx-5070-ti","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","ui-venus-1-5-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5070-ti","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5070-ti","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,84224,false,102.7,null,null],["nvidia-geforce-rtx-5070-ti","userrepgen-4b","cuda","fits","BF16",8192,10.23,85504,false,103.2,null,null],["nvidia-geforce-rtx-5070-ti","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,79.2,null,null],["nvidia-geforce-rtx-5070-ti","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,82.2,null,null],["nvidia-geforce-rtx-5070-ti","webworld-8b","cuda","fits","Q8_0",8192,10.39,25088,false,96.9,null,null],["nvidia-geforce-rtx-5070-ti","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,100864,false,142.9,null,null],["nvidia-geforce-rtx-5070-ti","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,466.7,null,null],["nvidia-geforce-rtx-5070-ti","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,466.7,null,null],["nvidia-geforce-rtx-5070-ti","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,203,null,null],["nvidia-geforce-rtx-5070-ti","zwz-2b","cuda","fits","F16",8192,5.62,71424,false,204.5,null,null],["nvidia-geforce-rtx-5070-ti","zwz-4b","cuda","fits","Q6_K",8192,5.74,56832,false,198.7,null,null],["nvidia-geforce-rtx-5070-ti","zwz-7b","cuda","fits","Q6_K",8192,7.47,100864,false,142.9,null,null],["nvidia-geforce-rtx-5070-ti","zwz-8b","cuda","fits","Q6_K",8192,8.59,37376,false,120.8,null,null],["nvidia-geforce-rtx-5080","aescode-32b","cuda","tight","Q3_K_M",8192,19.28,null,null,null,null,null],["nvidia-geforce-rtx-5080","aescode-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,56832,false,212.9,null,null],["nvidia-geforce-rtx-5080","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,158.1,null,null],["nvidia-geforce-rtx-5080","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,158.1,null,null],["nvidia-geforce-rtx-5080","ai21-jamba2-mini","cuda","tight","Q2_K",8192,19.01,null,null,null,null,null],["nvidia-geforce-rtx-5080","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,366.8,null,null],["nvidia-geforce-rtx-5080","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,366.8,null,null],["nvidia-geforce-rtx-5080","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,299,null,null],["nvidia-geforce-rtx-5080","apriel-1-6-15b-thinker","cuda","fits","Q5_K_M",8192,12.47,10240,false,84.1,null,null],["nvidia-geforce-rtx-5080","aprielguard","cuda","fits","Q6_K",8192,7.87,58880,false,142.8,null,null],["nvidia-geforce-rtx-5080","armorocr","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","astabrief-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","autoglm-phone-9b","cuda","fits","Q8_0",8192,10.8,57344,false,99.3,null,null],["nvidia-geforce-rtx-5080","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,118.8,null,null],["nvidia-geforce-rtx-5080","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5080","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5080","bielik-11b-v3-0-instruct","cuda","fits","Q6_K",8192,11.8,13312,false,89.4,null,null],["nvidia-geforce-rtx-5080","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,24320,false,104.9,null,null],["nvidia-geforce-rtx-5080","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,312.4,null,null],["nvidia-geforce-rtx-5080","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-geforce-rtx-5080","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"7",null],["nvidia-geforce-rtx-5080","contextpilot-14b","cuda","fits","Q5_K_M",8192,12.65,9472,false,83.1,null,null],["nvidia-geforce-rtx-5080","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","contextpilot-e4b","cuda","fits","F16",8192,10.89,118016,false,101.6,null,null],["nvidia-geforce-rtx-5080","cosmos-reason2-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,88,null,null],["nvidia-geforce-rtx-5080","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,173.6,null,null],["nvidia-geforce-rtx-5080","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-geforce-rtx-5080","deepseek-r1-0528-qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5080","deepseek-r1-distill-llama-8b","cuda","fits","Q8_0",8192,10.15,28928,false,106.1,null,null],["nvidia-geforce-rtx-5080","deepseek-r1-distill-qwen-14b","cuda","fits","Q5_K_M",8192,12.67,9216,false,82.9,null,null],["nvidia-geforce-rtx-5080","deepseek-r1-distill-qwen-32b","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5080","deepseek-r1-distill-qwen-7b","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-geforce-rtx-5080","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-geforce-rtx-5080","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-geforce-rtx-5080","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5080","devstral-small-2-24b-instruct-2512","cuda","fits","Q2_K",8192,11.09,18944,false,96,null,null],["nvidia-geforce-rtx-5080","eurollm-22b-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,92.1,null,null],["nvidia-geforce-rtx-5080","eurollm-22b-instruct-2512","cuda","fits","IQ3_XXS",8192,11.5,14336,false,92.1,null,null],["nvidia-geforce-rtx-5080","eurollm-9b-instruct-2512","cuda","fits","Q8_0",8192,11.65,15360,false,90.8,null,null],["nvidia-geforce-rtx-5080","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,1561.8,null,null],["nvidia-geforce-rtx-5080","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,"2",null],["nvidia-geforce-rtx-5080","fara-7b","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","fara1-5-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,90.4,null,null],["nvidia-geforce-rtx-5080","fara1-5-4b","cuda","fits","BF16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","fara1-5-9b","cuda","fits","Q8_0",8192,10.27,84224,false,110.1,null,null],["nvidia-geforce-rtx-5080","frogboss-32b-2510","cuda","fits","IQ2_XXS",8192,12.01,11264,false,88,null,null],["nvidia-geforce-rtx-5080","frogmini-14b-2510","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","frognano-4b-2609","cuda","fits","BF16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,1686.2,null,null],["nvidia-geforce-rtx-5080","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","gemma-2-27b-it","cuda","tight","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-2-9b-it","cuda","fits","Q6_K",8192,11.96,8192,false,96.8,null,null],["nvidia-geforce-rtx-5080","gemma-3-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,103.1,null,null],["nvidia-geforce-rtx-5080","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,469.4,null,null],["nvidia-geforce-rtx-5080","gemma-3-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,119.2,null,null],["nvidia-geforce-rtx-5080","gemma-4-12b","cuda","tight","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-4-12b-it","cuda","fits","Q6_K",8192,12.74,15360,false,93.8,null,null],["nvidia-geforce-rtx-5080","gemma-4-26b-a4b","cuda","tight","Q4_K_M",8192,19.09,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-4-26b-a4b-it","cuda","fits","IQ2_XXS",8192,12.09,43520,false,419.2,null,null],["nvidia-geforce-rtx-5080","gemma-4-31b","cuda","tight","Q3_K_M",8192,20.88,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-4-31b-it","cuda","tight","IQ4_XS",8192,21.95,null,null,null,null,null],["nvidia-geforce-rtx-5080","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,489.9,null,null],["nvidia-geforce-rtx-5080","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,206.3,null,null],["nvidia-geforce-rtx-5080","gemma-4-e4b","cuda","fits","F16",8192,11,111872,false,100.5,null,null],["nvidia-geforce-rtx-5080","gemma-4-e4b-it","cuda","fits","BF16",8192,11,111872,false,100.5,null,null],["nvidia-geforce-rtx-5080","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5080","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,"3",null],["nvidia-geforce-rtx-5080","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"5",null],["nvidia-geforce-rtx-5080","glm-4-6v-flash","cuda","fits","Q8_0",8192,10.8,57344,false,99.3,null,null],["nvidia-geforce-rtx-5080","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","glm-4-7-flash","cuda","fits","Q2_K",8192,12.77,9984,false,427.4,null,null],["nvidia-geforce-rtx-5080","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q3_K_M",8192,12.67,11776,false,383.9,null,null],["nvidia-geforce-rtx-5080","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"8",null],["nvidia-geforce-rtx-5080","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"7",null],["nvidia-geforce-rtx-5080","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-geforce-rtx-5080","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-geforce-rtx-5080","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5080","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5080","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5080","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"7",null],["nvidia-geforce-rtx-5080","gpt-oss-20b","cuda","fits","Q6_K",8192,12.83,9728,false,354.2,null,null],["nvidia-geforce-rtx-5080","granite-3-3-8b-instruct","cuda","fits","Q8_0",8192,11.11,18944,false,95.8,null,null],["nvidia-geforce-rtx-5080","granite-4-0-1b","cuda","fits","BF16",8192,5.14,102144,false,244,null,null],["nvidia-geforce-rtx-5080","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,1021.5,null,null],["nvidia-geforce-rtx-5080","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,320.9,null,null],["nvidia-geforce-rtx-5080","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,1342.8,null,null],["nvidia-geforce-rtx-5080","granite-4-1-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5080","granite-4-1-3b","cuda","fits","BF16",8192,8.61,59904,false,128.4,null,null],["nvidia-geforce-rtx-5080","granite-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,93.7,null,null],["nvidia-geforce-rtx-5080","granite-4-2-30b","cuda","tight","Q4_0",8192,19.41,null,null,null,null,null],["nvidia-geforce-rtx-5080","granite-4-2-3b","cuda","fits","BF16",8192,8.61,59904,false,128.4,null,null],["nvidia-geforce-rtx-5080","granite-4-2-8b","cuda","fits","Q8_0",8192,11.33,17664,false,93.7,null,null],["nvidia-geforce-rtx-5080","granite-guardian-3-2-8b-factuality-detection","cuda","fits","Q8_0",8192,11.11,18944,false,95.8,null,null],["nvidia-geforce-rtx-5080","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,107776,false,277.2,null,null],["nvidia-geforce-rtx-5080","granite-guardian-4-1-8b","cuda","fits","Q8_0",8192,11.33,17664,false,93.7,null,null],["nvidia-geforce-rtx-5080","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,59904,false,128.4,null,null],["nvidia-geforce-rtx-5080","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,132.8,null,null],["nvidia-geforce-rtx-5080","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,153.1,null,null],["nvidia-geforce-rtx-5080","hermes-4-3-36b","cuda","tight","IQ3_XXS",8192,16.93,null,null,null,null,null],["nvidia-geforce-rtx-5080","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,408.3,null,null],["nvidia-geforce-rtx-5080","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,1334.4,null,null],["nvidia-geforce-rtx-5080","holo-3-1-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5080","holo-3-1-4b","cuda","fits","F16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","holo-3-1-9b","cuda","fits","Q8_0",8192,10.25,84736,false,110.3,null,null],["nvidia-geforce-rtx-5080","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5080","holo2-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5080","holo2-4b","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","holo2-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","holo3-35b-a3b","cuda","tight","Q3_K_M",8192,18.15,null,null,null,null,null],["nvidia-geforce-rtx-5080","holo4-27b","cuda","fits","Q2_K",8192,12.74,10240,false,88.7,null,null],["nvidia-geforce-rtx-5080","holo4-35b-a3b","cuda","fits","IQ2_XXS",8192,11.98,48640,false,560,null,null],["nvidia-geforce-rtx-5080","holotron4-30b-a3b","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5080","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,509.7,null,null],["nvidia-geforce-rtx-5080","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"8",null],["nvidia-geforce-rtx-5080","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"4",null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","Q8_0",8192,10.15,28928,false,106.1,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.15,28928,false,106.1,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.15,28928,false,106.1,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","Q8_0",8192,10.15,28928,false,106.1,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","ising-calibration-1-35b-a3b","cuda","fits","IQ2_XXS",8192,11.07,89600,false,691.9,null,null],["nvidia-geforce-rtx-5080","ising-calibration-1-5-31b-bf16","cuda","tight","Q3_K_M",8192,21.5,null,null,null,null,null],["nvidia-geforce-rtx-5080","januscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","januscoder-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","januscoderv-7b","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,260.6,null,null],["nvidia-geforce-rtx-5080","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,129.1,null,null],["nvidia-geforce-rtx-5080","kat-coder-v2-5-dev","cuda","fits","IQ2_XXS",8192,11.35,77056,false,581.8,null,null],["nvidia-geforce-rtx-5080","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,"3",null],["nvidia-geforce-rtx-5080","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5080","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-geforce-rtx-5080","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5080","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5080","kimi-linear-48b-a3b-base","cuda","tight","Q2_K",8192,19.13,null,null,null,null,null],["nvidia-geforce-rtx-5080","kimi-linear-48b-a3b-instruct","cuda","tight","Q2_K",8192,18.65,null,null,null,null,null],["nvidia-geforce-rtx-5080","kimi-linear-reap-35b-a3b-instruct","cuda","fits","IQ2_M",8192,12.81,14848,false,722.1,null,null],["nvidia-geforce-rtx-5080","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","laguna-xs-2-1","cuda","fits","IQ2_XXS",8192,11.07,50944,false,526.5,null,null],["nvidia-geforce-rtx-5080","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,182,null,null],["nvidia-geforce-rtx-5080","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,182,null,null],["nvidia-geforce-rtx-5080","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,182,null,null],["nvidia-geforce-rtx-5080","lfm2-24b-a2b","cuda","tight","Q5_K_M",8192,18.03,null,null,null,null,null],["nvidia-geforce-rtx-5080","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,173.6,null,null],["nvidia-geforce-rtx-5080","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,408.9,null,null],["nvidia-geforce-rtx-5080","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,1713.8,null,null],["nvidia-geforce-rtx-5080","lfm2-5-24b-a2b","cuda","tight","Q5_K_M",8192,18.13,null,null,null,null,null],["nvidia-geforce-rtx-5080","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,1185.5,null,null],["nvidia-geforce-rtx-5080","lfm2-5-8b-a1b","cuda","fits","Q8_0",8192,10.2,128000,false,506.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,2451.1,null,null],["nvidia-geforce-rtx-5080","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,393.2,null,null],["nvidia-geforce-rtx-5080","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,173.6,null,null],["nvidia-geforce-rtx-5080","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,1185.5,null,null],["nvidia-geforce-rtx-5080","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,1185.5,null,null],["nvidia-geforce-rtx-5080","lfm2-8b-a1b","cuda","fits","Q8_0",8192,10.07,128000,false,545.3,null,null],["nvidia-geforce-rtx-5080","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,182,null,null],["nvidia-geforce-rtx-5080","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5080","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,"2",null],["nvidia-geforce-rtx-5080","llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,42496,false,132.8,null,null],["nvidia-geforce-rtx-5080","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,350.3,null,null],["nvidia-geforce-rtx-5080","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,46336,false,130.3,null,null],["nvidia-geforce-rtx-5080","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,"3",null],["nvidia-geforce-rtx-5080","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"4",null],["nvidia-geforce-rtx-5080","mathform-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,119.2,null,null],["nvidia-geforce-rtx-5080","mellum2-1-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.08,57600,false,456.7,null,null],["nvidia-geforce-rtx-5080","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,57600,false,456.7,null,null],["nvidia-geforce-rtx-5080","mellum2-12b-a2-5b-instruct","cuda","fits","Q6_K",8192,12.19,50688,false,433.6,null,null],["nvidia-geforce-rtx-5080","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,57600,false,456.7,null,null],["nvidia-geforce-rtx-5080","mellum2-12b-a2-5b-thinking","cuda","fits","Q6_K",8192,12.19,50688,false,433.6,null,null],["nvidia-geforce-rtx-5080","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,57600,false,456.7,null,null],["nvidia-geforce-rtx-5080","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,40448,false,138.1,null,null],["nvidia-geforce-rtx-5080","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-geforce-rtx-5080","mimo-v2-6-distill-qwen-9b","cuda","fits","Q8_0",8192,10.27,84224,false,110.1,null,null],["nvidia-geforce-rtx-5080","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5080","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5080","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","minicpm-o-4-5","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,597.8,null,null],["nvidia-geforce-rtx-5080","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,597.8,null,null],["nvidia-geforce-rtx-5080","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,597.8,null,null],["nvidia-geforce-rtx-5080","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,"2",null],["nvidia-geforce-rtx-5080","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,1039.5,null,null],["nvidia-geforce-rtx-5080","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,1039.5,null,null],["nvidia-geforce-rtx-5080","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,1039.5,null,null],["nvidia-geforce-rtx-5080","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,197.9,null,null],["nvidia-geforce-rtx-5080","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,221696,false,436.7,null,null],["nvidia-geforce-rtx-5080","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5080","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5080","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"8",null],["nvidia-geforce-rtx-5080","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"4",null],["nvidia-geforce-rtx-5080","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"6",null],["nvidia-geforce-rtx-5080","ministral-3-14b-instruct-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,91.5,null,null],["nvidia-geforce-rtx-5080","ministral-3-14b-reasoning-2512","cuda","fits","Q5_K_M",8192,11.57,16128,false,91.5,null,null],["nvidia-geforce-rtx-5080","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,45824,false,124.2,null,null],["nvidia-geforce-rtx-5080","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,45824,false,124.2,null,null],["nvidia-geforce-rtx-5080","ministral-3-8b-instruct-2512","cuda","fits","Q8_0",8192,10.68,23808,false,100.1,null,null],["nvidia-geforce-rtx-5080","ministral-3-8b-reasoning-2512","cuda","fits","Q8_0",8192,10.68,23808,false,100.1,null,null],["nvidia-geforce-rtx-5080","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,139,null,null],["nvidia-geforce-rtx-5080","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-geforce-rtx-5080","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"5",null],["nvidia-geforce-rtx-5080","mistral-nemo-instruct-2407","cuda","fits","Q6_K",8192,11.91,14080,false,88.6,null,null],["nvidia-geforce-rtx-5080","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q2_K",8192,11.09,18944,false,96,null,null],["nvidia-geforce-rtx-5080","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,"4",null],["nvidia-geforce-rtx-5080","muse-glimmer-30b","cuda","fits","IQ3_XXS",8192,12.61,24576,false,86.1,null,null],["nvidia-geforce-rtx-5080","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5080","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,276.4,null,null],["nvidia-geforce-rtx-5080","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,"3",null],["nvidia-geforce-rtx-5080","nemotron-cascade-14b-thinking","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","nemotron-cascade-2-30b-a3b","cuda","tight","Q4_0",8192,19.24,null,null,null,null,null],["nvidia-geforce-rtx-5080","nemotron-cascade-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","nemotron-cascade-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","nemotron-orchestrator-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","nemotron-terminal-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","nemotron-terminal-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,88,null,null],["nvidia-geforce-rtx-5080","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","north-mini-code-1-0","cuda","fits","IQ2_M",8192,12.7,9728,false,451.5,null,null],["nvidia-geforce-rtx-5080","nouscoder-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.27,null,null,null,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"7",null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.18,null,null,null,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,237312,false,132.2,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"5",null],["nvidia-geforce-rtx-5080","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"5",null],["nvidia-geforce-rtx-5080","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","tight","Q4_0",8192,19.03,null,null,null,null,null],["nvidia-geforce-rtx-5080","nvidia-nemotron-nano-9b-v2","cuda","fits","Q8_0",8192,10.63,131072,false,107.1,null,null],["nvidia-geforce-rtx-5080","olmo-3-1-32b-instruct","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5080","olmo-3-1-32b-instruct-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,96.7,null,null],["nvidia-geforce-rtx-5080","olmo-3-1-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5080","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-1-7b-rl-zero-math","cuda","fits","Q8_0",8192,12.68,8448,false,96,null,null],["nvidia-geforce-rtx-5080","olmo-3-1125-32b","cuda","fits","IQ2_XXS",8192,11.82,12032,false,96.7,null,null],["nvidia-geforce-rtx-5080","olmo-3-32b-think","cuda","tight","IQ4_XS",8192,20.12,null,null,null,null,null],["nvidia-geforce-rtx-5080","olmo-3-32b-think-dpo","cuda","fits","IQ2_XXS",8192,11.82,12032,false,96.7,null,null],["nvidia-geforce-rtx-5080","olmo-3-32b-think-sft","cuda","fits","IQ2_XXS",8192,11.82,12032,false,96.7,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-instruct","cuda","fits","Q8_0",8192,12.68,8448,false,96,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-think","cuda","fits","Q8_0",8192,12.68,8448,false,96,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,11520,false,115.2,null,null],["nvidia-geforce-rtx-5080","olmocr-2-7b-1025","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","optimind-sft","cuda","tight","Q5_K_M",8192,17.77,null,null,null,null,null],["nvidia-geforce-rtx-5080","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,19712,false,133.8,null,null],["nvidia-geforce-rtx-5080","phi-4","cuda","fits","Q5_K_M",8192,12.78,8448,false,81.8,null,null],["nvidia-geforce-rtx-5080","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,30208,false,109.8,null,null],["nvidia-geforce-rtx-5080","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,"4",null],["nvidia-geforce-rtx-5080","qwen2-5-14b-instruct","cuda","fits","Q5_K_M",8192,12.67,9216,false,82.9,null,null],["nvidia-geforce-rtx-5080","qwen2-5-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,268,null,null],["nvidia-geforce-rtx-5080","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,"3",null],["nvidia-geforce-rtx-5080","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,120.3,null,null],["nvidia-geforce-rtx-5080","qwen2-5-coder-32b-instruct","cuda","tight","Q3_K_M",8192,18.71,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,120.3,null,null],["nvidia-geforce-rtx-5080","qwen2-5-vl-7b-instruct","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","qwen2-5-vl-7b-surg-cholect50","cuda","fits","Q8_0",8192,9.15,72192,false,120.3,null,null],["nvidia-geforce-rtx-5080","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,450.3,null,null],["nvidia-geforce-rtx-5080","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,219.1,null,null],["nvidia-geforce-rtx-5080","qwen3-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5080","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,"2",null],["nvidia-geforce-rtx-5080","qwen3-30b-a3b-instruct-2507","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,"2",null],["nvidia-geforce-rtx-5080","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,175.1,null,null],["nvidia-geforce-rtx-5080","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,597.6,null,null],["nvidia-geforce-rtx-5080","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,1334.4,null,null],["nvidia-geforce-rtx-5080","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,"4",null],["nvidia-geforce-rtx-5080","qwen3-5-27b","cuda","tight","Q4_K_M",8192,18.36,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,248.4,null,null],["nvidia-geforce-rtx-5080","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,583.2,null,null],["nvidia-geforce-rtx-5080","qwen3-5-35b-a3b","cuda","tight","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-5-35b-a3b-base","cuda","fits","IQ2_XXS",8192,10.92,96512,false,777.9,null,null],["nvidia-geforce-rtx-5080","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-geforce-rtx-5080","qwen3-5-4b","cuda","fits","BF16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","qwen3-5-9b","cuda","fits","Q8_0",8192,10.25,84736,false,110.3,null,null],["nvidia-geforce-rtx-5080","qwen3-5-9b-base","cuda","fits","Q8_0",8192,10.25,84736,false,110.3,null,null],["nvidia-geforce-rtx-5080","qwen3-6-27b","cuda","tight","Q4_K_M",8192,18.43,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-6-35b-a3b","cuda","fits","IQ2_XXS",8192,11.35,77056,false,581.9,null,null],["nvidia-geforce-rtx-5080","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5080","qwen3-8-27b","cuda","fits","Q2_K",8192,12.48,14080,false,90.9,null,null],["nvidia-geforce-rtx-5080","qwen3-8-3-6-27b-blend","cuda","fits","Q2_K",8192,12.48,14080,false,90.9,null,null],["nvidia-geforce-rtx-5080","qwen3-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","qwen3-coder-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-geforce-rtx-5080","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,"3",null],["nvidia-geforce-rtx-5080","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,"2",null],["nvidia-geforce-rtx-5080","qwen3-coder-reap-25b-a3b","cuda","fits","IQ3_XXS",8192,11.77,19200,false,425.5,null,null],["nvidia-geforce-rtx-5080","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","qwen3-nemotron-14b-brrm","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"6",null],["nvidia-geforce-rtx-5080","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,"3",null],["nvidia-geforce-rtx-5080","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"8",null],["nvidia-geforce-rtx-5080","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-30b-a3b-instruct","cuda","tight","Q4_0",8192,18.97,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-32b-instruct","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-32b-thinking","cuda","tight","Q3_K_M",8192,18.75,null,null,null,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-8b-instruct","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","qwen3-vl-8b-thinking","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,"2",null],["nvidia-geforce-rtx-5080","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,200.5,null,null],["nvidia-geforce-rtx-5080","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","rnj-1-instruct","cuda","fits","Q8_0",8192,10.99,22528,false,96.9,null,null],["nvidia-geforce-rtx-5080","sera-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,88,null,null],["nvidia-geforce-rtx-5080","singguard-2b","cuda","fits","F16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,142.1,null,null],["nvidia-geforce-rtx-5080","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,307,null,null],["nvidia-geforce-rtx-5080","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,"3",null],["nvidia-geforce-rtx-5080","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,100864,false,153.1,null,null],["nvidia-geforce-rtx-5080","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,25088,false,103.7,null,null],["nvidia-geforce-rtx-5080","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"5",null],["nvidia-geforce-rtx-5080","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,"3",null],["nvidia-geforce-rtx-5080","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"4",null],["nvidia-geforce-rtx-5080","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"8",null],["nvidia-geforce-rtx-5080","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","tiny-aya-earth","cuda","fits","BF16",8192,8.72,190720,false,135.7,null,null],["nvidia-geforce-rtx-5080","tiny-aya-fire","cuda","fits","BF16",8192,8.72,190720,false,135.7,null,null],["nvidia-geforce-rtx-5080","tiny-aya-global","cuda","fits","BF16",8192,8.72,190720,false,135.7,null,null],["nvidia-geforce-rtx-5080","tiny-aya-water","cuda","fits","BF16",8192,8.72,190720,false,135.7,null,null],["nvidia-geforce-rtx-5080","translategemma-12b-it","cuda","fits","Q5_K_M",8192,11.83,23808,false,103.1,null,null],["nvidia-geforce-rtx-5080","translategemma-27b-it","cuda","tight","Q4_K_M",8192,20.35,null,null,null,null,null],["nvidia-geforce-rtx-5080","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,119.2,null,null],["nvidia-geforce-rtx-5080","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5080","trinity-mini","cuda","fits","IQ3_XXS",8192,12.12,48640,false,546.1,null,null],["nvidia-geforce-rtx-5080","trinity-mini-base","cuda","fits","IQ3_XXS",8192,11.76,68096,false,614.5,null,null],["nvidia-geforce-rtx-5080","trinity-mini-base-pre-anneal","cuda","fits","IQ3_XXS",4096,11.48,4096,false,642.1,null,null],["nvidia-geforce-rtx-5080","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,1066,null,null],["nvidia-geforce-rtx-5080","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,1140.3,null,null],["nvidia-geforce-rtx-5080","trinity-nano-preview","cuda","fits","Q8_0",8192,8.08,131072,false,875,null,null],["nvidia-geforce-rtx-5080","ui-mate-27b","cuda","fits","IQ2_M",8192,12.54,13312,false,90.4,null,null],["nvidia-geforce-rtx-5080","ui-mate-9b","cuda","fits","Q8_0",8192,10.27,84224,false,110.1,null,null],["nvidia-geforce-rtx-5080","ui-mate-democua-27b","cuda","fits","Q2_K",8192,12.74,10240,false,88.7,null,null],["nvidia-geforce-rtx-5080","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","ui-venus-1-5-30b-a3b","cuda","tight","IQ4_XS",8192,18.17,null,null,null,null,null],["nvidia-geforce-rtx-5080","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5080","ui-venus-2-9b","cuda","fits","Q8_0",8192,10.27,84224,false,110.1,null,null],["nvidia-geforce-rtx-5080","userrepgen-4b","cuda","fits","BF16",8192,10.23,85504,false,110.6,null,null],["nvidia-geforce-rtx-5080","webworld-14b","cuda","fits","Q5_K_M",8192,12.41,11008,false,84.8,null,null],["nvidia-geforce-rtx-5080","webworld-32b","cuda","fits","IQ2_XXS",8192,12.01,11264,false,88,null,null],["nvidia-geforce-rtx-5080","webworld-8b","cuda","fits","Q8_0",8192,10.39,25088,false,103.8,null,null],["nvidia-geforce-rtx-5080","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,100864,false,153.1,null,null],["nvidia-geforce-rtx-5080","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,500,null,null],["nvidia-geforce-rtx-5080","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,500,null,null],["nvidia-geforce-rtx-5080","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,217.5,null,null],["nvidia-geforce-rtx-5080","zwz-2b","cuda","fits","F16",8192,5.62,71424,false,219.1,null,null],["nvidia-geforce-rtx-5080","zwz-4b","cuda","fits","Q6_K",8192,5.74,56832,false,212.9,null,null],["nvidia-geforce-rtx-5080","zwz-7b","cuda","fits","Q6_K",8192,7.47,100864,false,153.1,null,null],["nvidia-geforce-rtx-5080","zwz-8b","cuda","fits","Q6_K",8192,8.59,37376,false,129.4,null,null],["nvidia-geforce-rtx-5090","aescode-32b","cuda","fits","Q5_K_M",8192,26.22,19712,false,70.5,null,null],["nvidia-geforce-rtx-5090","aescode-8b","cuda","fits","BF16",8192,17.35,89344,false,109.6,null,null],["nvidia-geforce-rtx-5090","agentcpm-explore","cuda","fits","Q6_K",8192,5.74,168448,false,397.5,null,null],["nvidia-geforce-rtx-5090","ai21-jamba-reasoning-3b","cuda","fits","BF16",8192,7.27,262144,false,295.1,null,null],["nvidia-geforce-rtx-5090","ai21-jamba2-3b","cuda","fits","BF16",8192,7.27,262144,false,295.1,null,null],["nvidia-geforce-rtx-5090","ai21-jamba2-mini","cuda","fits","IQ4_XS",8192,28.32,59904,false,273.8,null,null],["nvidia-geforce-rtx-5090","apertus-v1-1-1-5b","cuda","fits","F16",4096,3.84,4096,false,684.6,null,null],["nvidia-geforce-rtx-5090","apertus-v1-1-1-5b-instruct","cuda","fits","F16",4096,3.84,4096,false,684.6,null,null],["nvidia-geforce-rtx-5090","apertus-v1-1-4b","cuda","fits","Q6_K",4096,4.42,4096,false,558.1,null,null],["nvidia-geforce-rtx-5090","apriel-1-6-15b-thinker","cuda","fits","Q8_0",8192,17.19,69888,false,110.4,null,null],["nvidia-geforce-rtx-5090","aprielguard","cuda","fits","Q6_K",8192,7.87,131072,false,266.5,null,null],["nvidia-geforce-rtx-5090","armorocr","cuda","fits","Q8_0",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","astabrief-8b","cuda","fits","Q6_K",8192,8.59,40960,false,241.6,null,null],["nvidia-geforce-rtx-5090","autoglm-phone-9b","cuda","fits","F16",8192,18.87,65536,false,100.1,null,null],["nvidia-geforce-rtx-5090","autoglm-phone-9b-multilingual","cuda","fits","Q6_K",8192,9.25,65536,false,221.7,null,null],["nvidia-geforce-rtx-5090","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["nvidia-geforce-rtx-5090","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-geforce-rtx-5090","bielik-11b-v3-0-instruct","cuda","fits","BF16",8192,24.57,31232,false,75.4,null,null],["nvidia-geforce-rtx-5090","bielik-minitron-7b-v3-0-instruct","cuda","fits","Q8_0",8192,10.25,32768,false,195.9,null,null],["nvidia-geforce-rtx-5090","bitcpm-cann-3b-unquantized","cuda","fits","Q6_K",8192,4.29,32768,false,583.2,null,null],["nvidia-geforce-rtx-5090","caprl-qwen3vl-2b","cuda","fits","F16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","caprl-qwen3vl-4b","cuda","fits","F16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,"3",null],["nvidia-geforce-rtx-5090","contextpilot-14b","cuda","fits","Q8_0",8192,17.21,40960,false,110.6,null,null],["nvidia-geforce-rtx-5090","contextpilot-8b","cuda","fits","Q6_K",8192,8.59,40960,false,241.6,null,null],["nvidia-geforce-rtx-5090","contextpilot-e4b","cuda","fits","F16",8192,10.89,131072,false,189.7,null,null],["nvidia-geforce-rtx-5090","cosmos-reason2-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","cosmos-reason2-8b","cuda","fits","Q6_K",8192,8.59,148992,false,241.6,null,null],["nvidia-geforce-rtx-5090","d1-3b","cuda","fits","BF16",8192,6.7,32768,false,324.1,null,null],["nvidia-geforce-rtx-5090","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","deepseek-r1-0528-qwen3-8b","cuda","fits","BF16",8192,17.35,89344,false,109.6,null,null],["nvidia-geforce-rtx-5090","deepseek-r1-distill-llama-70b","cuda","tight","Q3_K_M",8192,37.05,null,null,null,null,null],["nvidia-geforce-rtx-5090","deepseek-r1-distill-llama-8b","cuda","fits","BF16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","deepseek-r1-distill-qwen-14b","cuda","fits","Q8_0",8192,17.48,68608,false,108.7,null,null],["nvidia-geforce-rtx-5090","deepseek-r1-distill-qwen-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","deepseek-r1-distill-qwen-7b","cuda","fits","F16",8192,15.65,131072,false,122.6,null,null],["nvidia-geforce-rtx-5090","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,"2",null],["nvidia-geforce-rtx-5090","devstral-small-2-24b-instruct-2512","cuda","fits","Q8_0",8192,26.45,25344,false,69.8,null,null],["nvidia-geforce-rtx-5090","eurollm-22b-2512","cuda","fits","Q6_K",8192,20.63,32768,false,90.8,null,null],["nvidia-geforce-rtx-5090","eurollm-22b-instruct-2512","cuda","fits","Q8_0",8192,25.82,23808,false,71.6,null,null],["nvidia-geforce-rtx-5090","eurollm-9b-instruct-2512","cuda","fits","F16",8192,19.58,32768,false,96,null,null],["nvidia-geforce-rtx-5090","euromoe-2-6b-a0-6b-instruct-2512","cuda","fits","Q6_K",8192,3.58,32768,false,2915.4,null,null],["nvidia-geforce-rtx-5090","exaone-4-5-33b","cuda","fits","Q6_K",8192,28.97,9216,false,65.4,null,null],["nvidia-geforce-rtx-5090","fara-7b","cuda","fits","BF16",8192,15.65,128000,false,122.6,null,null],["nvidia-geforce-rtx-5090","fara1-5-27b","cuda","fits","Q6_K",8192,24.39,81408,false,78.9,null,null],["nvidia-geforce-rtx-5090","fara1-5-4b","cuda","fits","BF16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","fara1-5-9b","cuda","fits","BF16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","frogboss-32b-2510","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","frogmini-14b-2510","cuda","fits","Q6_K",8192,13.89,40960,false,139.8,null,null],["nvidia-geforce-rtx-5090","frognano-4b-2609","cuda","fits","BF16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","functiongemma-270m-it","cuda","fits","BF16",8192,2.14,32768,false,3147.5,null,null],["nvidia-geforce-rtx-5090","gelab-zero-4b-preview","cuda","fits","BF16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","gemma-2-27b-it","cuda","fits","Q6_K",8192,26.47,8192,false,72.7,null,null],["nvidia-geforce-rtx-5090","gemma-2-9b-it","cuda","fits","Q8_0",8192,14.78,8192,false,140.1,null,null],["nvidia-geforce-rtx-5090","gemma-3-12b-it","cuda","fits","BF16",8192,26.63,47616,false,73.4,null,null],["nvidia-geforce-rtx-5090","gemma-3-1b-it","cuda","fits","BF16",8192,3.6,32768,false,876.2,null,null],["nvidia-geforce-rtx-5090","gemma-3-27b-it","cuda","fits","Q6_K",8192,25.86,49152,false,77,null,null],["nvidia-geforce-rtx-5090","gemma-3-4b-it","cuda","fits","BF16",8192,9.86,131072,false,222.6,null,null],["nvidia-geforce-rtx-5090","gemma-4-12b","cuda","fits","BF16",8192,26.51,159488,false,73.8,null,null],["nvidia-geforce-rtx-5090","gemma-4-12b-it","cuda","fits","BF16",8192,26.51,159488,false,73.8,null,null],["nvidia-geforce-rtx-5090","gemma-4-26b-a4b","cuda","fits","Q8_0",8192,28.96,21248,false,400.6,null,null],["nvidia-geforce-rtx-5090","gemma-4-26b-a4b-it","cuda","fits","Q8_0",8192,28.96,21248,false,400.6,null,null],["nvidia-geforce-rtx-5090","gemma-4-31b","cuda","fits","Q5_K_M",8192,27.31,31744,false,76.8,null,null],["nvidia-geforce-rtx-5090","gemma-4-31b-it","cuda","fits","Q5_K_M",8192,27.13,33792,false,77.4,null,null],["nvidia-geforce-rtx-5090","gemma-4-e2b","cuda","fits","Q6_K",8192,3.49,131072,false,914.6,null,null],["nvidia-geforce-rtx-5090","gemma-4-e2b-it","cuda","fits","BF16",8192,6.14,131072,false,385,null,null],["nvidia-geforce-rtx-5090","gemma-4-e4b","cuda","fits","F16",8192,11,131072,false,187.5,null,null],["nvidia-geforce-rtx-5090","gemma-4-e4b-it","cuda","fits","BF16",8192,11,131072,false,187.5,null,null],["nvidia-geforce-rtx-5090","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"5",null],["nvidia-geforce-rtx-5090","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,"2",null],["nvidia-geforce-rtx-5090","glm-4-5-air-reap-82b-a12b","cuda","tight","Q2_K",8192,36.51,null,null,null,null,null],["nvidia-geforce-rtx-5090","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"4",null],["nvidia-geforce-rtx-5090","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,"2",null],["nvidia-geforce-rtx-5090","glm-4-6v-flash","cuda","fits","BF16",8192,18.87,131072,false,100.1,null,null],["nvidia-geforce-rtx-5090","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"5",null],["nvidia-geforce-rtx-5090","glm-4-7-flash","cuda","fits","Q6_K",8192,25.71,72448,false,511.9,null,null],["nvidia-geforce-rtx-5090","glm-4-7-flash-reap-23b-a3b","cuda","fits","Q8_0",8192,25.4,78080,false,420.7,null,null],["nvidia-geforce-rtx-5090","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"4",null],["nvidia-geforce-rtx-5090","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"3",null],["nvidia-geforce-rtx-5090","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5090","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-geforce-rtx-5090","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-geforce-rtx-5090","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"4",null],["nvidia-geforce-rtx-5090","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,"3",null],["nvidia-geforce-rtx-5090","gpt-oss-20b","cuda","fits","Q8_0",8192,12.9,131072,false,644.8,null,null],["nvidia-geforce-rtx-5090","granite-3-3-8b-instruct","cuda","fits","F16",8192,18.62,73472,false,101.3,null,null],["nvidia-geforce-rtx-5090","granite-4-0-1b","cuda","fits","BF16",8192,5.14,131072,false,455.4,null,null],["nvidia-geforce-rtx-5090","granite-4-0-350m","cuda","fits","BF16",8192,2.2,32768,false,1906.9,null,null],["nvidia-geforce-rtx-5090","granite-4-0-h-1b","cuda","fits","BF16",8192,4.44,131072,false,599,null,null],["nvidia-geforce-rtx-5090","granite-4-0-h-350m","cuda","fits","BF16",8192,2.07,32768,false,2506.6,null,null],["nvidia-geforce-rtx-5090","granite-4-1-30b","cuda","fits","Q6_K",8192,26.6,18176,false,69.4,null,null],["nvidia-geforce-rtx-5090","granite-4-1-3b","cuda","fits","BF16",8192,8.61,131072,false,239.7,null,null],["nvidia-geforce-rtx-5090","granite-4-1-8b","cuda","fits","BF16",8192,19.03,70912,false,99,null,null],["nvidia-geforce-rtx-5090","granite-4-2-30b","cuda","fits","Q6_K",8192,26.6,18176,false,69.4,null,null],["nvidia-geforce-rtx-5090","granite-4-2-3b","cuda","fits","BF16",8192,8.61,131072,false,239.7,null,null],["nvidia-geforce-rtx-5090","granite-4-2-8b","cuda","fits","BF16",8192,19.03,70912,false,99,null,null],["nvidia-geforce-rtx-5090","granite-guardian-3-2-8b-factuality-detection","cuda","fits","F16",8192,18.62,73472,false,101.3,null,null],["nvidia-geforce-rtx-5090","granite-guardian-4-0-3b-toxicity-ja","cuda","fits","Q6_K",8192,4.67,131072,false,517.4,null,null],["nvidia-geforce-rtx-5090","granite-guardian-4-1-8b","cuda","fits","BF16",8192,19.03,70912,false,99,null,null],["nvidia-geforce-rtx-5090","granite-vision-4-1-4b","cuda","fits","BF16",8192,8.61,131072,false,239.7,null,null],["nvidia-geforce-rtx-5090","harc-llama-3-1-8b-instruct","cuda","fits","Q6_K",8192,8.37,131072,false,247.8,null,null],["nvidia-geforce-rtx-5090","harc-qwen2-5-7b-instruct","cuda","fits","Q6_K",8192,7.47,32768,false,285.8,null,null],["nvidia-geforce-rtx-5090","hermes-4-3-36b","cuda","fits","Q5_K_M",8192,27.98,13056,false,65.9,null,null],["nvidia-geforce-rtx-5090","hipo-1-7b","cuda","fits","Q6_K",8192,3.63,40960,false,762.1,null,null],["nvidia-geforce-rtx-5090","holo-3-1-0-8b","cuda","fits","Q6_K",8192,2.3,262144,false,2490.8,null,null],["nvidia-geforce-rtx-5090","holo-3-1-35b-a3b","cuda","fits","Q5_K_M",8192,25.83,163072,false,749.3,null,null],["nvidia-geforce-rtx-5090","holo-3-1-4b","cuda","fits","F16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","holo-3-1-9b","cuda","fits","F16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["nvidia-geforce-rtx-5090","holo2-30b-a3b","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","holo2-4b","cuda","fits","F16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","holo2-8b","cuda","fits","Q6_K",8192,8.59,148992,false,241.6,null,null],["nvidia-geforce-rtx-5090","holo3-35b-a3b","cuda","fits","Q5_K_M",8192,25.83,163072,false,749.3,null,null],["nvidia-geforce-rtx-5090","holo4-27b","cuda","fits","Q6_K",8192,23.27,98304,false,83.1,null,null],["nvidia-geforce-rtx-5090","holo4-35b-a3b","cuda","fits","Q5_K_M",8192,27.85,71424,false,584.7,null,null],["nvidia-geforce-rtx-5090","holotron4-30b-a3b","cuda","fits","Q5_K_M",8192,26.79,262144,true,657,null,null],["nvidia-geforce-rtx-5090","hunyuanocr","cuda","fits","F16",8192,3.13,32768,false,951.5,null,null],["nvidia-geforce-rtx-5090","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"3",null],["nvidia-geforce-rtx-5090","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,"2",null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-llama3-8b-baseline","cuda","fits","F16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","fits","F16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","fits","F16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-llama3-8b-multiview","cuda","fits","F16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-4b-baseline","cuda","fits","F16",8192,10.39,40960,false,193.7,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","fits","F16",8192,10.39,40960,false,193.7,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","fits","F16",8192,10.39,40960,false,193.7,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-4b-multiview","cuda","fits","F16",8192,10.39,40960,false,193.7,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-8b-baseline","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","intent-aware-lfqa-qwen3-8b-multiview","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"5",null],["nvidia-geforce-rtx-5090","ising-calibration-1-35b-a3b","cuda","fits","Q5_K_M",8192,25.83,163072,false,749.3,null,null],["nvidia-geforce-rtx-5090","ising-calibration-1-5-31b-bf16","cuda","fits","Q5_K_M",8192,28.06,22528,false,74.3,null,null],["nvidia-geforce-rtx-5090","januscoder-14b","cuda","fits","Q8_0",8192,17.21,32768,false,110.6,null,null],["nvidia-geforce-rtx-5090","januscoder-8b","cuda","fits","BF16",8192,17.35,32768,false,109.6,null,null],["nvidia-geforce-rtx-5090","januscoderv-7b","cuda","fits","BF16",8192,15.65,128000,false,122.6,null,null],["nvidia-geforce-rtx-5090","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"6",null],["nvidia-geforce-rtx-5090","kanana-2-3b-base","cuda","fits","Q6_K",8192,4.89,32768,false,486.5,null,null],["nvidia-geforce-rtx-5090","kanana-2-3b-instruct","cuda","fits","F16",8192,8.57,32768,false,241,null,null],["nvidia-geforce-rtx-5090","kat-coder-v2-5-dev","cuda","fits","Q5_K_M",8192,26.11,150272,false,668.7,null,null],["nvidia-geforce-rtx-5090","kat-dev-72b-exp","cuda","fits","IQ2_XXS",8192,28.54,10240,false,64.6,null,null],["nvidia-geforce-rtx-5090","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-geforce-rtx-5090","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-geforce-rtx-5090","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-geforce-rtx-5090","kimi-linear-48b-a3b-base","cuda","fits","Q4_0",8192,28.69,64256,false,908.8,null,null],["nvidia-geforce-rtx-5090","kimi-linear-48b-a3b-instruct","cuda","fits","IQ4_XS",8192,27.33,201984,false,862.3,null,null],["nvidia-geforce-rtx-5090","kimi-linear-reap-35b-a3b-instruct","cuda","fits","Q5_K_M",8192,25.78,262144,true,765.7,null,null],["nvidia-geforce-rtx-5090","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"8",null],["nvidia-geforce-rtx-5090","laguna-xs-2-1","cuda","fits","Q5_K_M",8192,25.31,101376,false,667.5,null,null],["nvidia-geforce-rtx-5090","lfm2-2-6b-exp","cuda","fits","F16",8192,6.45,128000,false,339.8,null,null],["nvidia-geforce-rtx-5090","lfm2-2-6b-longevity","cuda","fits","F16",8192,6.45,128000,false,339.8,null,null],["nvidia-geforce-rtx-5090","lfm2-2-6b-transcript","cuda","fits","BF16",8192,6.45,128000,false,339.8,null,null],["nvidia-geforce-rtx-5090","lfm2-24b-a2b","cuda","fits","Q8_0",8192,26.3,128000,false,674.8,null,null],["nvidia-geforce-rtx-5090","lfm2-5-1-2b-base","cuda","fits","BF16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-1-2b-instruct","cuda","fits","BF16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-1-2b-jp","cuda","fits","F16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-1-2b-jp-202606","cuda","fits","F16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-1-2b-thinking","cuda","fits","BF16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-2-6b","cuda","fits","BF16",8192,6.7,131072,false,324.1,null,null],["nvidia-geforce-rtx-5090","lfm2-5-2-6b-base","cuda","fits","Q6_K",8192,3.58,128000,false,763.3,null,null],["nvidia-geforce-rtx-5090","lfm2-5-230m","cuda","fits","BF16",8192,1.83,128000,false,3199.1,null,null],["nvidia-geforce-rtx-5090","lfm2-5-24b-a2b","cuda","fits","Q8_0",8192,26.43,131072,false,641.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-350m","cuda","fits","BF16",8192,2.07,128000,false,2213,null,null],["nvidia-geforce-rtx-5090","lfm2-5-8b-a1b","cuda","fits","BF16",8192,17.99,128000,false,515.6,null,null],["nvidia-geforce-rtx-5090","lfm2-5-encoder-350m-diffusion","cuda","fits","Q6_K",8192,1.66,128000,false,4575.4,null,null],["nvidia-geforce-rtx-5090","lfm2-5-vl-1-6b","cuda","fits","BF16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-vl-1-6b-extract","cuda","fits","F16",8192,3.67,128000,false,733.9,null,null],["nvidia-geforce-rtx-5090","lfm2-5-vl-3b","cuda","fits","BF16",8192,6.7,32768,false,324.1,null,null],["nvidia-geforce-rtx-5090","lfm2-5-vl-450m","cuda","fits","BF16",8192,2.07,128000,false,2213,null,null],["nvidia-geforce-rtx-5090","lfm2-5-vl-450m-extract","cuda","fits","F16",8192,2.07,128000,false,2213,null,null],["nvidia-geforce-rtx-5090","lfm2-8b-a1b","cuda","fits","F16",8192,17.73,128000,false,556.6,null,null],["nvidia-geforce-rtx-5090","lfm2-vl-3b","cuda","fits","BF16",8192,6.45,128000,false,339.8,null,null],["nvidia-geforce-rtx-5090","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-geforce-rtx-5090","llama-3-1-70b-instruct","cuda","fits","IQ2_M",8192,27.11,14592,false,68,null,null],["nvidia-geforce-rtx-5090","llama-3-1-8b-instruct","cuda","fits","BF16",8192,17.05,101632,false,111.4,null,null],["nvidia-geforce-rtx-5090","llama-3-2-1b-instruct","cuda","fits","BF16",8192,3.97,131072,false,654,null,null],["nvidia-geforce-rtx-5090","llama-3-2-3b-instruct","cuda","fits","BF16",8192,8.5,131072,false,243.3,null,null],["nvidia-geforce-rtx-5090","llama-3-3-70b-instruct","cuda","tight","Q3_K_M",8192,37.05,null,null,null,null,null],["nvidia-geforce-rtx-5090","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,"2",null],["nvidia-geforce-rtx-5090","mathform-8b","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","medgemma-1-5-4b-it","cuda","fits","BF16",8192,9.86,131072,false,222.6,null,null],["nvidia-geforce-rtx-5090","mellum2-1-12b-a2-5b-thinking","cuda","fits","BF16",8192,24.98,131072,false,390,null,null],["nvidia-geforce-rtx-5090","mellum2-12b-a2-5b-base","cuda","fits","Q6_K",8192,12.08,131072,false,852.5,null,null],["nvidia-geforce-rtx-5090","mellum2-12b-a2-5b-instruct","cuda","fits","BF16",8192,24.98,131072,false,390,null,null],["nvidia-geforce-rtx-5090","mellum2-12b-a2-5b-instruct-sft","cuda","fits","Q6_K",8192,12.08,131072,false,852.5,null,null],["nvidia-geforce-rtx-5090","mellum2-12b-a2-5b-thinking","cuda","fits","BF16",8192,24.98,131072,false,390,null,null],["nvidia-geforce-rtx-5090","mellum2-12b-a2-5b-thinking-sft","cuda","fits","Q6_K",8192,12.08,131072,false,852.5,null,null],["nvidia-geforce-rtx-5090","mimo-embodied-7b","cuda","fits","Q6_K",8192,8.14,128000,false,257.7,null,null],["nvidia-geforce-rtx-5090","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"4",null],["nvidia-geforce-rtx-5090","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","mimo-v2-6-distill-qwen-9b","cuda","fits","BF16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"5",null],["nvidia-geforce-rtx-5090","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"5",null],["nvidia-geforce-rtx-5090","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5090","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-geforce-rtx-5090","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"5",null],["nvidia-geforce-rtx-5090","minicpm-o-4-5","cuda","fits","F16",8192,17.34,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","minicpm-v-4-6","cuda","fits","F16",8192,3.17,262144,false,1115.8,null,null],["nvidia-geforce-rtx-5090","minicpm-v-4-6-thinking","cuda","fits","F16",8192,3.17,262144,false,1115.8,null,null],["nvidia-geforce-rtx-5090","minicpm-v-4-7-1b","cuda","fits","F16",8192,3.17,262144,false,1115.8,null,null],["nvidia-geforce-rtx-5090","minicpm-v-4-7-35b-a3b","cuda","fits","Q5_K_M",8192,25.83,163072,false,749.4,null,null],["nvidia-geforce-rtx-5090","minicpm5-1b","cuda","fits","Q6_K",8192,2.18,131072,false,1940.4,null,null],["nvidia-geforce-rtx-5090","minicpm5-1b-base","cuda","fits","Q6_K",8192,2.18,131072,false,1940.4,null,null],["nvidia-geforce-rtx-5090","minicpm5-1b-sft","cuda","fits","Q6_K",8192,2.18,131072,false,1940.4,null,null],["nvidia-geforce-rtx-5090","minicpm5-2b","cuda","fits","BF16",8192,6.04,131072,false,369.4,null,null],["nvidia-geforce-rtx-5090","minicpm5-2b-base","cuda","fits","Q6_K",8192,3.43,262144,true,815.3,null,null],["nvidia-geforce-rtx-5090","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"4",null],["nvidia-geforce-rtx-5090","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"4",null],["nvidia-geforce-rtx-5090","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"4",null],["nvidia-geforce-rtx-5090","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,"2",null],["nvidia-geforce-rtx-5090","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,"3",null],["nvidia-geforce-rtx-5090","ministral-3-14b-instruct-2512","cuda","fits","BF16",8192,27.76,17152,false,66.3,null,null],["nvidia-geforce-rtx-5090","ministral-3-14b-reasoning-2512","cuda","fits","BF16",8192,27.76,17152,false,66.3,null,null],["nvidia-geforce-rtx-5090","ministral-3-3b-instruct-2512","cuda","fits","BF16",8192,8.86,199680,false,231.8,null,null],["nvidia-geforce-rtx-5090","ministral-3-3b-reasoning-2512","cuda","fits","BF16",8192,8.86,199680,false,231.8,null,null],["nvidia-geforce-rtx-5090","ministral-3-8b-instruct-2512","cuda","fits","BF16",8192,17.99,89344,false,105.1,null,null],["nvidia-geforce-rtx-5090","ministral-3-8b-reasoning-2512","cuda","fits","BF16",8192,17.99,89344,false,105.1,null,null],["nvidia-geforce-rtx-5090","mistral-7b-instruct-v0-2","cuda","fits","Q6_K",8192,8.05,32768,false,259.4,null,null],["nvidia-geforce-rtx-5090","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"8:tight",null],["nvidia-geforce-rtx-5090","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,"2",null],["nvidia-geforce-rtx-5090","mistral-nemo-instruct-2407","cuda","fits","F16",8192,25.29,32512,false,73.2,null,null],["nvidia-geforce-rtx-5090","mistral-small-3-2-24b-instruct-2506","cuda","fits","Q8_0",8192,26.45,25344,false,69.8,null,null],["nvidia-geforce-rtx-5090","mistral-small-4-119b-2603","cuda","tight","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-geforce-rtx-5090","muse-glimmer-30b","cuda","fits","Q6_K",8192,23.73,131072,false,79.7,null,null],["nvidia-geforce-rtx-5090","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-geforce-rtx-5090","nemotron-3-content-safety","cuda","fits","Q6_K",8192,5.37,131072,false,515.9,null,null],["nvidia-geforce-rtx-5090","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","fits","Q4_K_M",8192,23.26,262144,false,602.7,null,null],["nvidia-geforce-rtx-5090","nemotron-cascade-14b-thinking","cuda","fits","Q8_0",8192,17.21,32768,false,110.6,null,null],["nvidia-geforce-rtx-5090","nemotron-cascade-2-30b-a3b","cuda","fits","Q5_K_M",8192,26.96,262144,false,617.9,null,null],["nvidia-geforce-rtx-5090","nemotron-cascade-8b","cuda","fits","BF16",8192,17.35,32768,false,109.6,null,null],["nvidia-geforce-rtx-5090","nemotron-cascade-8b-thinking","cuda","fits","BF16",8192,17.35,32768,false,109.6,null,null],["nvidia-geforce-rtx-5090","nemotron-orchestrator-8b","cuda","fits","BF16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","nemotron-terminal-14b","cuda","fits","Q6_K",8192,13.89,40960,false,139.8,null,null],["nvidia-geforce-rtx-5090","nemotron-terminal-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","nemotron-terminal-8b","cuda","fits","Q6_K",8192,8.59,40960,false,241.6,null,null],["nvidia-geforce-rtx-5090","north-mini-code-1-0","cuda","fits","Q6_K",8192,28.24,20992,false,509.1,null,null],["nvidia-geforce-rtx-5090","nouscoder-14b","cuda","fits","Q8_0",8192,17.21,81920,false,110.6,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","fits","Q5_K_M",8192,26.59,262144,false,660,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","fits","Q5_K_M",8192,26.96,262144,false,617.9,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,"3",null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","fits","Q5_K_M",8192,26.89,262144,false,631.7,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-nano-4b-bf16","cuda","fits","BF16",8192,8.73,262144,false,246.8,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,"2",null],["nvidia-geforce-rtx-5090","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,"2",null],["nvidia-geforce-rtx-5090","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","fits","Q5_K_M",8192,26.79,262144,false,657,null,null],["nvidia-geforce-rtx-5090","nvidia-nemotron-nano-9b-v2","cuda","fits","BF16",8192,18.26,131072,false,107,null,null],["nvidia-geforce-rtx-5090","olmo-3-1-32b-instruct","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-1-32b-instruct-dpo","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-1-32b-think","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-1-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-1-7b-rl-zero-math","cuda","fits","F16",8192,19.01,60672,false,108.9,null,null],["nvidia-geforce-rtx-5090","olmo-3-1125-32b","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-32b-think","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-32b-think-dpo","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-32b-think-sft","cuda","fits","Q6_K",8192,28.91,9472,false,65.5,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-instruct","cuda","fits","BF16",8192,19.01,60672,false,108.9,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-instruct-dpo","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-instruct-sft","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-rl-zero-code","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-rl-zero-general","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-rl-zero-if","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-rl-zero-math","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-rl-zero-mix","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-think","cuda","fits","BF16",8192,19.01,60672,false,108.9,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-think-dpo","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmo-3-7b-think-sft","cuda","fits","Q6_K",8192,11.05,65536,false,215,null,null],["nvidia-geforce-rtx-5090","olmocr-2-7b-1025","cuda","fits","BF16",8192,15.65,128000,false,122.6,null,null],["nvidia-geforce-rtx-5090","optimind-sft","cuda","fits","Q6_K",8192,22.79,131072,false,450.3,null,null],["nvidia-geforce-rtx-5090","phi-3-5-mini-instruct","cuda","fits","Q8_0",8192,8.32,62208,false,249.7,null,null],["nvidia-geforce-rtx-5090","phi-4","cuda","fits","Q8_0",8192,17.66,16384,false,107.2,null,null],["nvidia-geforce-rtx-5090","phi-4-mini-instruct","cuda","fits","BF16",8192,9.99,131072,false,204.9,null,null],["nvidia-geforce-rtx-5090","qwen-agentworld-35b-a3b","cuda","tight","Q8_0",8192,37.57,null,null,null,null,null],["nvidia-geforce-rtx-5090","qwen2-5-14b-instruct","cuda","fits","Q8_0",8192,17.48,32768,false,108.7,null,null],["nvidia-geforce-rtx-5090","qwen2-5-32b-instruct","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","qwen2-5-3b-instruct","cuda","fits","Q8_0",8192,4.83,32768,false,500.3,null,null],["nvidia-geforce-rtx-5090","qwen2-5-72b-instruct","cuda","tight","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-geforce-rtx-5090","qwen2-5-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,224.5,null,null],["nvidia-geforce-rtx-5090","qwen2-5-coder-32b-instruct","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","qwen2-5-coder-7b-instruct","cuda","fits","Q8_0",8192,9.15,32768,false,224.5,null,null],["nvidia-geforce-rtx-5090","qwen2-5-vl-7b-instruct","cuda","fits","BF16",8192,15.65,128000,false,122.6,null,null],["nvidia-geforce-rtx-5090","qwen2-5-vl-7b-surg-cholect50","cuda","fits","F16",8192,15.65,128000,false,122.6,null,null],["nvidia-geforce-rtx-5090","qwen3-0-6b","cuda","fits","BF16",8192,3.41,40960,false,840.6,null,null],["nvidia-geforce-rtx-5090","qwen3-1-7b","cuda","fits","BF16",8192,5.62,40960,false,409,null,null],["nvidia-geforce-rtx-5090","qwen3-14b","cuda","fits","Q8_0",8192,17.21,40960,false,110.6,null,null],["nvidia-geforce-rtx-5090","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"6",null],["nvidia-geforce-rtx-5090","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"4",null],["nvidia-geforce-rtx-5090","qwen3-30b-a3b","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","qwen3-30b-a3b-instruct-2507","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","qwen3-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","qwen3-4b","cuda","fits","Q8_0",8192,6.7,40960,false,326.9,null,null],["nvidia-geforce-rtx-5090","qwen3-4b-instruct-2507","cuda","fits","F16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","qwen3-5-0-8b","cuda","fits","BF16",8192,3.17,262144,false,1115.5,null,null],["nvidia-geforce-rtx-5090","qwen3-5-0-8b-base","cuda","fits","Q6_K",8192,2.3,262144,false,2490.8,null,null],["nvidia-geforce-rtx-5090","qwen3-5-122b-a10b","cuda","tight","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-geforce-rtx-5090","qwen3-5-27b","cuda","fits","Q6_K",8192,23.64,92672,false,81.7,null,null],["nvidia-geforce-rtx-5090","qwen3-5-2b","cuda","fits","BF16",8192,5.38,262144,false,463.6,null,null],["nvidia-geforce-rtx-5090","qwen3-5-2b-base","cuda","fits","Q6_K",8192,3.21,262144,false,1088.6,null,null],["nvidia-geforce-rtx-5090","qwen3-5-35b-a3b","cuda","fits","Q5_K_M",8192,27.13,103936,false,591.3,null,null],["nvidia-geforce-rtx-5090","qwen3-5-35b-a3b-base","cuda","fits","Q5_K_M",8192,25.86,161536,false,738.3,null,null],["nvidia-geforce-rtx-5090","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"7",null],["nvidia-geforce-rtx-5090","qwen3-5-4b","cuda","fits","BF16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","qwen3-5-4b-base","cuda","fits","F16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","qwen3-5-9b","cuda","fits","BF16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","qwen3-5-9b-base","cuda","fits","F16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","qwen3-6-27b","cuda","fits","Q6_K",8192,23.7,91648,false,81.4,null,null],["nvidia-geforce-rtx-5090","qwen3-6-35b-a3b","cuda","fits","Q5_K_M",8192,26.11,150272,false,669.2,null,null],["nvidia-geforce-rtx-5090","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-geforce-rtx-5090","qwen3-8-27b","cuda","fits","Q6_K",8192,24.78,75520,false,77.6,null,null],["nvidia-geforce-rtx-5090","qwen3-8-3-6-27b-blend","cuda","fits","Q6_K",8192,24.78,75520,false,77.6,null,null],["nvidia-geforce-rtx-5090","qwen3-8b","cuda","fits","Q8_0",8192,10.39,40960,false,193.7,null,null],["nvidia-geforce-rtx-5090","qwen3-coder-30b-a3b-instruct","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"7",null],["nvidia-geforce-rtx-5090","qwen3-coder-next","cuda","tight","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-geforce-rtx-5090","qwen3-coder-next-base","cuda","fits","IQ2_M",8192,27.24,85248,false,1076,null,null],["nvidia-geforce-rtx-5090","qwen3-coder-reap-25b-a3b","cuda","fits","Q8_0",8192,27.72,23552,false,440.8,null,null],["nvidia-geforce-rtx-5090","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"5",null],["nvidia-geforce-rtx-5090","qwen3-nemotron-14b-brrm","cuda","fits","Q6_K",8192,13.89,40960,false,139.8,null,null],["nvidia-geforce-rtx-5090","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,"3",null],["nvidia-geforce-rtx-5090","qwen3-nemotron-8b-brrm","cuda","fits","Q6_K",8192,8.59,40960,false,241.6,null,null],["nvidia-geforce-rtx-5090","qwen3-next-80b-a3b-instruct","cuda","tight","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"4",null],["nvidia-geforce-rtx-5090","qwen3-vl-2b-instruct","cuda","fits","BF16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-2b-thinking","cuda","fits","BF16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-30b-a3b-instruct","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-32b-instruct","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-32b-thinking","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-4b-instruct","cuda","fits","BF16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-4b-thinking","cuda","fits","BF16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-8b-instruct","cuda","fits","BF16",8192,17.35,89344,false,109.6,null,null],["nvidia-geforce-rtx-5090","qwen3-vl-8b-thinking","cuda","fits","BF16",8192,17.35,89344,false,109.6,null,null],["nvidia-geforce-rtx-5090","qwq-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","riva-translate-4b-instruct-v1-1","cuda","fits","Q6_K",8192,5.97,8192,false,374.2,null,null],["nvidia-geforce-rtx-5090","rlvr-8b-0926","cuda","fits","Q6_K",8192,8.59,148992,false,241.6,null,null],["nvidia-geforce-rtx-5090","rnj-1-instruct","cuda","fits","BF16",8192,18.63,32768,false,101.3,null,null],["nvidia-geforce-rtx-5090","sera-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","singguard-2b","cuda","fits","F16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","smollm3-3b","cuda","fits","BF16",8192,7.9,65536,false,265.3,null,null],["nvidia-geforce-rtx-5090","smollm3-3b-gsm8k-sft","cuda","fits","Q6_K",8192,4.35,65536,false,573.1,null,null],["nvidia-geforce-rtx-5090","solar-open-100b","cuda","tight","IQ2_M",8192,35.79,null,null,null,null,null],["nvidia-geforce-rtx-5090","spatial-ssrl-7b","cuda","fits","Q6_K",8192,7.47,128000,false,285.8,null,null],["nvidia-geforce-rtx-5090","spatial-ssrl-qwen3vl-4b","cuda","fits","F16",8192,10.39,136704,false,193.7,null,null],["nvidia-geforce-rtx-5090","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,"2",null],["nvidia-geforce-rtx-5090","step-3-5-flash-reap-121b-a11b","cuda","tight","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-geforce-rtx-5090","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,"2",null],["nvidia-geforce-rtx-5090","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"3",null],["nvidia-geforce-rtx-5090","step3-vl-10b-base","cuda","fits","Q6_K",8192,8.59,40960,false,241.6,null,null],["nvidia-geforce-rtx-5090","tiny-aya-earth","cuda","fits","BF16",8192,8.72,262144,true,253.2,null,null],["nvidia-geforce-rtx-5090","tiny-aya-fire","cuda","fits","BF16",8192,8.72,262144,true,253.2,null,null],["nvidia-geforce-rtx-5090","tiny-aya-global","cuda","fits","BF16",8192,8.72,262144,true,253.2,null,null],["nvidia-geforce-rtx-5090","tiny-aya-water","cuda","fits","BF16",8192,8.72,262144,true,253.2,null,null],["nvidia-geforce-rtx-5090","translategemma-12b-it","cuda","fits","Q8_0",8192,15.82,131072,false,134,null,null],["nvidia-geforce-rtx-5090","translategemma-27b-it","cuda","fits","Q6_K",8192,25.86,49152,false,77,null,null],["nvidia-geforce-rtx-5090","translategemma-4b-it","cuda","fits","F16",8192,9.86,131072,false,222.6,null,null],["nvidia-geforce-rtx-5090","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"4",null],["nvidia-geforce-rtx-5090","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"5",null],["nvidia-geforce-rtx-5090","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"4",null],["nvidia-geforce-rtx-5090","trinity-mini","cuda","fits","Q8_0",8192,28.77,33280,false,509.8,null,null],["nvidia-geforce-rtx-5090","trinity-mini-base","cuda","fits","Q6_K",8192,22.67,131072,false,645.8,null,null],["nvidia-geforce-rtx-5090","trinity-mini-base-pre-anneal","cuda","fits","Q6_K",4096,22.39,4096,false,661.8,null,null],["nvidia-geforce-rtx-5090","trinity-nano-base","cuda","fits","Q6_K",8192,6.67,131072,false,1989.8,null,null],["nvidia-geforce-rtx-5090","trinity-nano-base-pre-anneal","cuda","fits","Q6_K",4096,6.43,4096,false,2128.6,null,null],["nvidia-geforce-rtx-5090","trinity-nano-preview","cuda","fits","BF16",8192,13.51,131072,false,964.5,null,null],["nvidia-geforce-rtx-5090","ui-mate-27b","cuda","fits","Q6_K",8192,24.39,81408,false,78.9,null,null],["nvidia-geforce-rtx-5090","ui-mate-9b","cuda","fits","BF16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","ui-mate-democua-27b","cuda","fits","Q6_K",8192,23.27,98304,false,83.1,null,null],["nvidia-geforce-rtx-5090","ui-venus-1-5-2b","cuda","fits","F16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","ui-venus-1-5-30b-a3b","cuda","fits","Q6_K",8192,26.45,36608,false,536.3,null,null],["nvidia-geforce-rtx-5090","ui-venus-1-5-8b","cuda","fits","Q6_K",8192,8.59,148992,false,241.6,null,null],["nvidia-geforce-rtx-5090","ui-venus-2-9b","cuda","fits","BF16",8192,17.55,262144,false,111,null,null],["nvidia-geforce-rtx-5090","userrepgen-4b","cuda","fits","BF16",8192,10.23,262144,false,206.4,null,null],["nvidia-geforce-rtx-5090","webworld-14b","cuda","fits","Q6_K",8192,13.89,40960,false,139.8,null,null],["nvidia-geforce-rtx-5090","webworld-32b","cuda","fits","Q6_K",8192,29.15,8448,false,63.1,null,null],["nvidia-geforce-rtx-5090","webworld-8b","cuda","fits","F16",8192,17.35,40960,false,109.6,null,null],["nvidia-geforce-rtx-5090","x-reasoner-7b","cuda","fits","Q6_K",8192,7.47,128000,false,285.8,null,null],["nvidia-geforce-rtx-5090","youtu-llm-2b","cuda","fits","Q6_K",8192,3.16,131072,false,933.4,null,null],["nvidia-geforce-rtx-5090","youtu-llm-2b-base","cuda","fits","Q6_K",8192,3.16,131072,false,933.4,null,null],["nvidia-geforce-rtx-5090","youtu-vl-4b-instruct","cuda","fits","Q6_K",8192,5.91,32768,false,406,null,null],["nvidia-geforce-rtx-5090","zwz-2b","cuda","fits","F16",8192,5.62,214528,false,409,null,null],["nvidia-geforce-rtx-5090","zwz-4b","cuda","fits","Q6_K",8192,5.74,168448,false,397.5,null,null],["nvidia-geforce-rtx-5090","zwz-7b","cuda","fits","Q6_K",8192,7.47,128000,false,285.8,null,null],["nvidia-geforce-rtx-5090","zwz-8b","cuda","fits","Q6_K",8192,8.59,148992,false,241.6,null,null],["nvidia-h100-nvl","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","baichuan-m3-235b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,null,null],["nvidia-h100-nvl","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-h100-nvl","command-a-plus-05-2026-bf16","cuda","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-h100-nvl","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-h100-nvl","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-h100-nvl","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-h100-nvl","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-h100-nvl","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-6-reap-268b-a32b","cuda","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-h100-nvl","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-7-reap-218b-a32b","cuda","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-4-7-reap-268b-a32b","cuda","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-h100-nvl","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-h100-nvl","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-h100-nvl","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-h100-nvl","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-h100-nvl","glm-5-3-flash-bf16","cuda","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gpt-oss-120b","cuda","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo2-235b-a22b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","hy3","cuda","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-h100-nvl","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-h100-nvl","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-h100-nvl","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-h100-nvl","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-h100-nvl","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-h100-nvl","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","laguna-s-2-1","cuda","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-h100-nvl","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mimo-v2-5","cuda","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-h100-nvl","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-h100-nvl","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-h100-nvl","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h100-nvl","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h100-nvl","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-h100-nvl","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minimax-m2","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minimax-m2-1","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minimax-m2-5","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","minimax-m2-7","cuda","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-h100-nvl","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-h100-nvl","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-h100-nvl","qwen3-235b-a22b-instruct-2507","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-h100-nvl","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-h100-nvl","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-h100-nvl","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-h100-nvl","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-nemotron-235b-a22b-genrm","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-235b-a22b-instruct","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","step-3-7-flash","cuda","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-large-base","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-large-thinking","cuda","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-large-truebase","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-nvl","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","baichuan-m3-235b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,null,null],["nvidia-h100-pcie","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-h100-pcie","command-a-plus-05-2026-bf16","cuda","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-h100-pcie","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-h100-pcie","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-h100-pcie","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-h100-pcie","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-h100-pcie","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-h100-pcie","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-h100-pcie","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-7-reap-218b-a32b","cuda","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-4-7-reap-268b-a32b","cuda","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-h100-pcie","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-h100-pcie","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-h100-pcie","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-h100-pcie","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-h100-pcie","glm-5-3-flash-bf16","cuda","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gpt-oss-120b","cuda","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo2-235b-a22b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","hy3","cuda","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-h100-pcie","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-h100-pcie","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-h100-pcie","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-h100-pcie","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-h100-pcie","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-h100-pcie","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-h100-pcie","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-h100-pcie","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mimo-v2-5","cuda","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-h100-pcie","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-h100-pcie","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-h100-pcie","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h100-pcie","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h100-pcie","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-h100-pcie","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minimax-m2","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minimax-m2-1","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minimax-m2-5","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","minimax-m2-7","cuda","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-h100-pcie","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-h100-pcie","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-h100-pcie","qwen3-235b-a22b-instruct-2507","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-h100-pcie","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-h100-pcie","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-h100-pcie","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-h100-pcie","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-nemotron-235b-a22b-genrm","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-235b-a22b-instruct","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","step-3-7-flash","cuda","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-h100-pcie","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-h100-pcie","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-h100-pcie","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h100-pcie","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","baichuan-m3-235b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,null,null],["nvidia-h200-sxm","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-h200-sxm","command-a-plus-05-2026-bf16","cuda","na","IQ2_XXS",8192,63.63,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-h200-sxm","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-h200-sxm","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-h200-sxm","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-h200-sxm","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-5","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-6-reap-268b-a32b","cuda","na","Q2_K",8192,100.87,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-7","cuda","na","Q2_K",8192,130.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-7-reap-218b-a32b","cuda","na","Q2_K",8192,82.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-4-7-reap-268b-a32b","cuda","na","IQ2_XXS",8192,73.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-h200-sxm","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-h200-sxm","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-h200-sxm","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,null,null],["nvidia-h200-sxm","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-h200-sxm","glm-5-3-flash-bf16","cuda","na","IQ2_XXS",8192,91.96,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gpt-oss-120b","cuda","na","Q2_K",8192,62.76,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo2-235b-a22b","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","hy3","cuda","na","IQ2_XXS",8192,82.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","intern-s2-397b","cuda","na","IQ2_XXS",8192,114.31,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","k-exaone-236b-a23b","cuda","na","IQ4_XS",8192,126.29,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-h200-sxm","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-h200-sxm","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-h200-sxm","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-h200-sxm","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","laguna-s-2-1","cuda","na","Q4_K_M",8192,95.87,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-h200-sxm","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-v2-5","cuda","na","IQ2_XXS",8192,82.44,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-h200-sxm","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-v2-6-flash-mopd","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-v2-6-flash-rl","cuda","na","Q2_K",8192,124.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h200-sxm","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-h200-sxm","mimo-v2-flash","cuda","na","Q2_K",8192,111.57,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minimax-m2","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minimax-m2-1","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minimax-m2-5","cuda","na","Q2_K",8192,84.92,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","minimax-m2-7","cuda","na","IQ2_XXS",8192,62.9,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-h200-sxm","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-h200-sxm","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","na","Q4_0",8192,71.85,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-235b-a22b","cuda","na","Q4_K_M",8192,141.88,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-235b-a22b-instruct-2507","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-h200-sxm","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-h200-sxm","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-h200-sxm","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-coder-reap-363b-a35b","cuda","na","Q2_K",8192,132.69,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-nemotron-235b-a22b-genrm","cuda","na","IQ2_XXS",8192,63.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-235b-a22b-instruct","cuda","na","Q2_K",8192,86.67,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","step-3-7-flash","cuda","na","IQ3_XXS",8192,76.06,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-large-base","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-large-thinking","cuda","na","IQ2_XXS",8192,107.1,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-large-truebase","cuda","na","IQ2_XXS",8192,96.44,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-h200-sxm","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-l4","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-l4","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-l4","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-l4","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-l4","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-l4","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-l4","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-l4","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-l4","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-l4","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l4","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-l4","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-l4","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-l4","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l4","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-l4","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-l4","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-l4","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-l4","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-l4","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-l4","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-l4","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-l4","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l4","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-l4","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-l4","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l4","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-l4","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-l4","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-l4","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-l4","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-l4","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-l4","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-l4","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-l4","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-l4","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-l4","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l4","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-l4","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-l4","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l4","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l4","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l4","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l4","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-l4","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-l4","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-l4","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-l4","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-l4","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-l4","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-l4","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-l4","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-l4","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-l4","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-l4","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-l4","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,null,null],["nvidia-l4","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["nvidia-l4","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-l4","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-l4","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-l4","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-l4","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-l4","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["nvidia-l4","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-l4","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-l4","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-l4","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-l4","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l4","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-l4","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-l4","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-l4","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-l4","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-l4","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-l4","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l4","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l4","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-l4","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-l4","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-l4","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l4","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-l4","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["nvidia-l4","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["nvidia-l4","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-l4","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-l4","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-l4","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-l4","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l4","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-l4","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-l4","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-l4","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-l4","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-l4","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-l4","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-l4","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-l4","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-l4","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-l4","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-l4","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-l4","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-l4","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-l4","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l4","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-l4","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-l4","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l4","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-l4","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l4","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-l4","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,null,null],["nvidia-l4","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-l4","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l4","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-l4","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["nvidia-l4","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-l4","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-l4","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-l4","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-l4","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-l4","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-l4","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-l4","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-l4","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-l4","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l4","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l4","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l4","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["nvidia-l4","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-l4","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-l4","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-l4","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l4","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l4","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-l4","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-l4","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-l4","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-l4","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-l4","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-l4","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-l4","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-l4","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-l4","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-l4","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l4","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-l4","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-l4","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["nvidia-l4","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["nvidia-l4","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l4","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l4","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l4","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-l4","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-l4","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-l4","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,null,null],["nvidia-l4","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-l4","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-l4","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-l4","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-l4","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-l4","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-l4","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-l4","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-l4","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-l4","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l4","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-l4","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-l4","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-l4","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-l4","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-l4","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l4","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-l4","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-l4","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-l4","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l4","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l4","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["nvidia-l4","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-l4","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["nvidia-l4","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["nvidia-l4","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l4","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l4","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l4","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l4","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-l4","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-l4","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-l4","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-l4","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-l4","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-l4","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l4","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l4","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l4","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l4","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l4","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l4","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l4","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-l4","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-l4","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l4","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-l4","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-l4","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l4","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-l40","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-l40","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-l40","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-l40","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-l40","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-l40","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-l40","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-l40","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-l40","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-l40","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l40","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-l40","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-l40","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-l40","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l40","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-l40","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-l40","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-l40","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-l40","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-l40","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-l40","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-l40","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-l40","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l40","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-l40","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l40","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-l40","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-l40","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-l40","devstral-2-123b-instruct-2512","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-l40","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-l40","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-l40","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-l40","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-l40","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-l40","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-l40","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l40","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-l40","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-l40","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l40","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l40","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l40","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l40","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-l40","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-l40","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-l40","glm-4-5-air","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-l40","glm-4-6v","cuda","na","Q2_K",8192,45.62,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-l40","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-l40","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,null,null],["nvidia-l40","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["nvidia-l40","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-l40","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-l40","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-l40","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-l40","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,null,null],["nvidia-l40","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["nvidia-l40","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-l40","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-l40","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-l40","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-l40","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l40","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-l40","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-l40","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-l40","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-l40","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-l40","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-l40","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l40","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l40","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-l40","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-l40","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-l40","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l40","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-l40","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["nvidia-l40","intellect-3","cuda","na","IQ2_XXS",8192,39.58,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-l40","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-l40","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-l40","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-l40","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l40","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-l40","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-l40","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-l40","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-l40","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-l40","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,null,null],["nvidia-l40","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-l40","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,null,null],["nvidia-l40","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,null,null],["nvidia-l40","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-l40","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-l40","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-l40","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-l40","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-l40","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l40","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,null,null],["nvidia-l40","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-l40","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-l40","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-l40","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l40","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-l40","llama-4-scout-17b-16e-instruct","cuda","na","Q2_K",8192,41.46,null,null,null,null,"no_measured_total"],["nvidia-l40","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-l40","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-l40","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-l40","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["nvidia-l40","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-l40","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-l40","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-l40","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-l40","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-l40","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,null,null],["nvidia-l40","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-l40","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-l40","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-l40","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l40","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l40","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-l40","minimax-m2-5-reap-139b-a10b","cuda","na","IQ2_XXS",8192,39.25,null,null,null,null,"no_measured_total"],["nvidia-l40","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-l40","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-l40","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-l40","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l40","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-l40","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-l40","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-l40","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-l40","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-l40","mistral-medium-3-5-128b","cuda","na","Q2_K",8192,49.32,null,null,null,null,"no_measured_total"],["nvidia-l40","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-l40","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-l40","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-l40","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-l40","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,null,null],["nvidia-l40","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l40","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-l40","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-l40","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","na","IQ2_XXS",8192,49.78,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","na","IQ2_XXS",8192,51.01,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-l40","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-l40","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-l40","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-l40","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-l40","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-l40","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-l40","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-l40","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-l40","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-l40","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-l40","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-l40","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-l40","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-l40","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-l40","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-l40","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-l40","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l40","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-l40","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-l40","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-l40","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l40","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-l40","step-3-5-flash","cuda","na","IQ2_XXS",8192,48.93,null,null,null,null,"no_measured_total"],["nvidia-l40","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-l40","step-3-5-flash-reap-149b-a11b","cuda","na","IQ2_XXS",8192,40.14,null,null,null,null,"no_measured_total"],["nvidia-l40","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["nvidia-l40","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l40","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l40","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l40","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-l40","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-l40","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-l40","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-l40","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-l40","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-l40","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-l40","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-l40","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-l40","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l40","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-l40","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-l40","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-l40","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l40","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-l40","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-l40","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-l40","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-l40","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-l40","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-l40","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-p100","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-p100","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-p100","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-p100","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-p100","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-p100","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-p100","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-p100","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-p100","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-p100","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p100","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-p100","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-p100","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-p100","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p100","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-p100","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-p100","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-p100","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-p100","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-p100","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-p100","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-p100","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-p100","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-p100","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-p100","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-p100","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p100","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-p100","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-p100","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-p100","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-p100","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-p100","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-p100","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-p100","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-p100","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-p100","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,null,null],["nvidia-p100","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p100","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-p100","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-p100","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p100","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-p100","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p100","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p100","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-p100","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-p100","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-p100","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-p100","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-p100","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-p100","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-p100","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-p100","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-p100","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-p100","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-p100","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-p100","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,null,null],["nvidia-p100","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["nvidia-p100","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-p100","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-p100","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-p100","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-p100","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-p100","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["nvidia-p100","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-p100","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-p100","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-p100","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-p100","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p100","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-p100","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-p100","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-p100","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-p100","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-p100","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-p100","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p100","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-p100","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-p100","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-p100","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-p100","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-p100","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-p100","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["nvidia-p100","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["nvidia-p100","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-p100","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-p100","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-p100","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-p100","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p100","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-p100","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-p100","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-p100","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-p100","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-p100","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-p100","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-p100","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-p100","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-p100","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-p100","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-p100","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-p100","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-p100","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-p100","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p100","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-p100","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,null,null],["nvidia-p100","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p100","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-p100","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p100","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-p100","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,null,null],["nvidia-p100","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-p100","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p100","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-p100","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["nvidia-p100","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-p100","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-p100","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-p100","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-p100","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-p100","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-p100","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-p100","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,null,null],["nvidia-p100","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-p100","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-p100","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-p100","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-p100","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-p100","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["nvidia-p100","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-p100","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-p100","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-p100","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p100","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p100","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-p100","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-p100","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-p100","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-p100","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-p100","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-p100","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-p100","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-p100","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-p100","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-p100","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-p100","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-p100","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-p100","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-p100","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["nvidia-p100","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["nvidia-p100","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-p100","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p100","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p100","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-p100","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-p100","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-p100","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,null,null],["nvidia-p100","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-p100","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-p100","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-p100","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,null,null],["nvidia-p100","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,null,null],["nvidia-p100","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-p100","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-p100","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-p100","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-p100","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-p100","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,null,null],["nvidia-p100","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-p100","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p100","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-p100","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-p100","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,null,null],["nvidia-p100","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-p100","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-p100","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-p100","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-p100","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-p100","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-p100","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p100","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p100","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["nvidia-p100","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-p100","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["nvidia-p100","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["nvidia-p100","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p100","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p100","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p100","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p100","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-p100","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-p100","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-p100","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-p100","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-p100","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-p100","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p100","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p100","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p100","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p100","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-p100","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p100","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p100","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-p100","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-p100","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p100","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-p100","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-p100","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p100","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","aescode-32b","cuda","no","IQ2_XXS",8192,13.6,null,null,null,null,null],["nvidia-p4","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-p4","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-p4","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-p4","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-p4","ai21-jamba2-mini","cuda","no","IQ2_XXS",8192,13.63,null,null,null,null,null],["nvidia-p4","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-p4","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-p4","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-p4","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-p4","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p4","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-p4","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-p4","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-p4","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p4","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-p4","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-p4","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-p4","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-p4","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-p4","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-p4","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-p4","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-p4","cosmos-reason2-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-p4","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-p4","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-p4","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-p4","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-p4","deepseek-r1-distill-qwen-32b","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-p4","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p4","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-p4","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-p4","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-p4","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-p4","devstral-small-2-24b-instruct-2512","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-p4","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-p4","eurollm-22b-instruct-2512","cuda","no","IQ2_M",8192,10.57,null,null,null,null,null],["nvidia-p4","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-p4","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-p4","exaone-4-5-33b","cuda","no","IQ4_XS",8192,20.43,null,null,null,null,null],["nvidia-p4","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p4","fara1-5-27b","cuda","no","IQ2_M",8192,12.54,null,null,null,null,null],["nvidia-p4","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-p4","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p4","frogboss-32b-2510","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-p4","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p4","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p4","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-p4","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-2-27b-it","cuda","no","IQ2_M",8192,13.78,null,null,null,null,null],["nvidia-p4","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-3-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-p4","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-4-12b","cuda","no","Q8_0",8192,15.57,null,null,null,null,null],["nvidia-p4","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-4-26b-a4b","cuda","no","Q2_K",8192,13,null,null,null,null,null],["nvidia-p4","gemma-4-26b-a4b-it","cuda","no","IQ2_XXS",8192,12.09,null,null,null,null,null],["nvidia-p4","gemma-4-31b","cuda","no","Q2_K",8192,17.58,null,null,null,null,null],["nvidia-p4","gemma-4-31b-it","cuda","no","Q3_K_M",8192,20.34,null,null,null,null,null],["nvidia-p4","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-p4","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-p4","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-p4","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-p4","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-p4","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,"over",null],["nvidia-p4","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-p4","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-p4","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,"over",null],["nvidia-p4","glm-4-7-flash","cuda","no","Q2_K",8192,12.77,null,null,null,null,null],["nvidia-p4","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-p4","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,"over",null],["nvidia-p4","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,"over",null],["nvidia-p4","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-p4","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,"over",null],["nvidia-p4","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-p4","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-p4","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-p4","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,"over",null],["nvidia-p4","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-p4","gpt-oss-20b","cuda","no","Q2_K",8192,12.56,null,null,null,null,null],["nvidia-p4","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-1-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-p4","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-2-30b","cuda","no","Q2_K",8192,13.89,null,null,null,null,null],["nvidia-p4","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-p4","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-p4","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-p4","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p4","hermes-4-3-36b","cuda","no","IQ2_XXS",8192,12.89,null,null,null,null,null],["nvidia-p4","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-p4","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-p4","holo-3-1-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-p4","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-p4","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-p4","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p4","holo2-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-p4","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","holo3-35b-a3b","cuda","no","Q2_K",8192,14.45,null,null,null,null,null],["nvidia-p4","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-p4","holo4-35b-a3b","cuda","no","IQ2_XXS",8192,11.98,null,null,null,null,null],["nvidia-p4","holotron4-30b-a3b","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-p4","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-p4","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,"over",null],["nvidia-p4","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["nvidia-p4","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,"over",null],["nvidia-p4","ising-calibration-1-35b-a3b","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-p4","ising-calibration-1-5-31b-bf16","cuda","no","IQ2_XXS",8192,16.51,null,null,null,null,null],["nvidia-p4","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-p4","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p4","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,"over",null],["nvidia-p4","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-p4","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-p4","kat-coder-v2-5-dev","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-p4","kat-dev-72b-exp","cuda","no","IQ2_XXS",8192,28.54,null,null,null,null,null],["nvidia-p4","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-p4","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-p4","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-p4","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-p4","kimi-linear-48b-a3b-base","cuda","no","IQ2_XXS",8192,14.24,null,null,null,null,null],["nvidia-p4","kimi-linear-48b-a3b-instruct","cuda","no","IQ2_XXS",8192,13.35,null,null,null,null,null],["nvidia-p4","kimi-linear-reap-35b-a3b-instruct","cuda","no","IQ2_XXS",8192,10.67,null,null,null,null,null],["nvidia-p4","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,"over",null],["nvidia-p4","laguna-xs-2-1","cuda","no","IQ2_XXS",8192,11.07,null,null,null,null,null],["nvidia-p4","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-24b-a2b","cuda","no","Q4_0",8192,14.65,null,null,null,null,null],["nvidia-p4","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-24b-a2b","cuda","no","Q4_0",8192,14.75,null,null,null,null,null],["nvidia-p4","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-p4","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p4","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-p4","llama-3-1-70b-instruct","cuda","no","IQ2_XXS",8192,22.29,null,null,null,null,null],["nvidia-p4","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-p4","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-p4","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p4","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-p4","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,null,null],["nvidia-p4","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-p4","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-p4","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-p4","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,"over",null],["nvidia-p4","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-p4","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-p4","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-p4","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,"over",null],["nvidia-p4","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-p4","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-p4","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,"over",null],["nvidia-p4","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm-v-4-7-35b-a3b","cuda","no","IQ4_XS",8192,20.02,null,null,null,null,null],["nvidia-p4","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-p4","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-p4","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-p4","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-p4","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,"over",null],["nvidia-p4","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["nvidia-p4","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-p4","ministral-3-14b-instruct-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-p4","ministral-3-14b-reasoning-2512","cuda","no","Q4_K_M",8192,10.29,null,null,null,null,null],["nvidia-p4","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p4","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-p4","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-p4","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-p4","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-p4","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-p4","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-p4","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-p4","mistral-small-3-2-24b-instruct-2506","cuda","no","Q2_K",8192,11.09,null,null,null,null,null],["nvidia-p4","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-p4","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-p4","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-p4","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","no","Q4_K_M",8192,23.26,null,null,null,null,null],["nvidia-p4","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-cascade-2-30b-a3b","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-p4","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p4","nemotron-terminal-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-p4","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","north-mini-code-1-0","cuda","no","IQ2_XXS",8192,10.7,null,null,null,null,null],["nvidia-p4","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-p4","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","no","Q2_K",8192,18.88,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","no","IQ2_M",8192,19.07,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","no","IQ4_XS",8192,19.09,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-p4","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","no","IQ2_M",8192,18.88,null,null,null,null,null],["nvidia-p4","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-1-32b-instruct","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-p4","olmo-3-1-32b-instruct-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-p4","olmo-3-1-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-p4","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-1125-32b","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-p4","olmo-3-32b-think","cuda","no","Q2_K",8192,15,null,null,null,null,null],["nvidia-p4","olmo-3-32b-think-dpo","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-p4","olmo-3-32b-think-sft","cuda","no","IQ2_XXS",8192,11.82,null,null,null,null,null],["nvidia-p4","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-p4","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-p4","optimind-sft","cuda","no","IQ2_M",8192,13.14,null,null,null,null,null],["nvidia-p4","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-p4","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-p4","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,null,null],["nvidia-p4","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen2-5-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-p4","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-p4","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen2-5-coder-32b-instruct","cuda","no","Q2_K",8192,15.24,null,null,null,null,null],["nvidia-p4","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-14b","cuda","no","Q4_K_M",8192,11.03,null,null,null,null,null],["nvidia-p4","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,"over",null],["nvidia-p4","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-p4","qwen3-30b-a3b","cuda","no","Q4_K_M",8192,20.13,null,null,null,null,null],["nvidia-p4","qwen3-30b-a3b-instruct-2507","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-p4","qwen3-32b","cuda","no","Q4_K_M",8192,22.37,null,null,null,null,null],["nvidia-p4","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-p4","qwen3-5-27b","cuda","no","Q3_K_M",8192,15.35,null,null,null,null,null],["nvidia-p4","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-35b-a3b","cuda","no","Q3_K_M",8192,17.55,null,null,null,null,null],["nvidia-p4","qwen3-5-35b-a3b-base","cuda","no","IQ2_XXS",8192,10.92,null,null,null,null,null],["nvidia-p4","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,"over",null],["nvidia-p4","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-6-27b","cuda","no","Q3_K_M",8192,15.43,null,null,null,null,null],["nvidia-p4","qwen3-6-35b-a3b","cuda","no","IQ2_XXS",8192,11.35,null,null,null,null,null],["nvidia-p4","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-p4","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-coder-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-p4","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,"over",null],["nvidia-p4","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-p4","qwen3-coder-next-base","cuda","no","IQ2_XXS",8192,22.32,null,null,null,null,null],["nvidia-p4","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,"over",null],["nvidia-p4","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-p4","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-p4","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,"over",null],["nvidia-p4","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-vl-30b-a3b-instruct","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-p4","qwen3-vl-32b-instruct","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-p4","qwen3-vl-32b-thinking","cuda","no","Q2_K",8192,15.27,null,null,null,null,null],["nvidia-p4","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","qwq-32b","cuda","no","Q4_K_M",8192,22.45,null,null,null,null,null],["nvidia-p4","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-p4","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-p4","sera-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-p4","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-p4","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-p4","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-p4","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p4","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-p4","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["nvidia-p4","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-p4","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["nvidia-p4","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,"over",null],["nvidia-p4","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p4","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p4","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p4","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-p4","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-p4","translategemma-27b-it","cuda","no","Q2_K",8192,14.43,null,null,null,null,null],["nvidia-p4","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-p4","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,"over",null],["nvidia-p4","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,"over",null],["nvidia-p4","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-p4","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-p4","ui-mate-27b","cuda","no","IQ2_XXS",8192,11.21,null,null,null,null,null],["nvidia-p4","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p4","ui-mate-democua-27b","cuda","no","Q2_K",8192,12.74,null,null,null,null,null],["nvidia-p4","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-p4","ui-venus-1-5-30b-a3b","cuda","no","Q2_K",8192,13.04,null,null,null,null,null],["nvidia-p4","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-p4","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-p4","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p4","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-p4","webworld-32b","cuda","no","IQ2_XXS",8192,12.01,null,null,null,null,null],["nvidia-p4","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-p4","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p4","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-p4","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-p4","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-p4","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-p4","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-p4","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-p4","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-p40","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-tesla-p40","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,"over",null],["nvidia-tesla-p40","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-tesla-p40","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,"over",null],["nvidia-tesla-p40","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-r1-distill-llama-70b","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-tesla-p40","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,"over",null],["nvidia-tesla-p40","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,"over",null],["nvidia-tesla-p40","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,"over",null],["nvidia-tesla-p40","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-tesla-p40","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-tesla-p40","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-tesla-p40","glm-4-5-air-reap-82b-a12b","cuda","no","IQ2_XXS",8192,31.08,null,null,null,null,null],["nvidia-tesla-p40","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-tesla-p40","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-tesla-p40","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-tesla-p40","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,null,null],["nvidia-tesla-p40","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["nvidia-tesla-p40","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,"over",null],["nvidia-tesla-p40","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-tesla-p40","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-tesla-p40","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-tesla-p40","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-tesla-p40","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["nvidia-tesla-p40","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-tesla-p40","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-p40","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["nvidia-tesla-p40","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["nvidia-tesla-p40","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-tesla-p40","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-tesla-p40","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-tesla-p40","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,"over",null],["nvidia-tesla-p40","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-tesla-p40","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-tesla-p40","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-tesla-p40","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-tesla-p40","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","llama-3-3-70b-instruct","cuda","no","Q2_K",8192,29.42,null,null,null,null,null],["nvidia-tesla-p40","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,null,null],["nvidia-tesla-p40","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["nvidia-tesla-p40","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,"over",null],["nvidia-tesla-p40","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-tesla-p40","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-tesla-p40","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-tesla-p40","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-tesla-p40","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-tesla-p40","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-p40","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-p40","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-p40","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["nvidia-tesla-p40","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-tesla-p40","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,"over",null],["nvidia-tesla-p40","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-tesla-p40","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","mistral-small-4-119b-2603","cuda","no","IQ2_XXS",8192,34.29,null,null,null,null,null],["nvidia-tesla-p40","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-tesla-p40","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-tesla-p40","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["nvidia-tesla-p40","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["nvidia-tesla-p40","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen-agentworld-35b-a3b","cuda","no","Q8_0",8192,37.57,null,null,null,null,null],["nvidia-tesla-p40","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-72b-instruct","cuda","no","Q2_K",8192,30.34,null,null,null,null,null],["nvidia-tesla-p40","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-tesla-p40","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-tesla-p40","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-122b-a10b","cuda","no","IQ2_XXS",8192,35.03,null,null,null,null,null],["nvidia-tesla-p40","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-tesla-p40","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-tesla-p40","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-tesla-p40","qwen3-coder-next","cuda","no","Q2_K",8192,30.37,null,null,null,null,null],["nvidia-tesla-p40","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-tesla-p40","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-p40","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-next-80b-a3b-instruct","cuda","no","Q2_K",8192,30.32,null,null,null,null,null],["nvidia-tesla-p40","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-tesla-p40","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","solar-open-100b","cuda","no","IQ2_XXS",8192,29.36,null,null,null,null,null],["nvidia-tesla-p40","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["nvidia-tesla-p40","step-3-5-flash-reap-121b-a11b","cuda","no","IQ2_XXS",8192,32.92,null,null,null,null,null],["nvidia-tesla-p40","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["nvidia-tesla-p40","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["nvidia-tesla-p40","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-tesla-p40","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-tesla-p40","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-tesla-p40","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-p40","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","aescode-32b","cuda","na","IQ2_XXS",8192,13.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","aescode-8b","cuda","na","IQ2_M",8192,5.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","agentcpm-explore","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ai21-jamba-reasoning-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ai21-jamba2-3b","cuda","na","IQ2_M",8192,2.36,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ai21-jamba2-mini","cuda","na","IQ2_XXS",8192,13.63,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","apertus-v1-1-1-5b","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","apertus-v1-1-1-5b-instruct","cuda","na","Q2_K",4096,1.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","apertus-v1-1-4b","cuda","na","IQ2_XXS",4096,2.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","apriel-1-6-15b-thinker","cuda","na","IQ2_M",8192,7.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","aprielguard","cuda","na","IQ2_XXS",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","armorocr","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","astabrief-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","autoglm-phone-9b","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","autoglm-phone-9b-multilingual","cuda","na","IQ2_XXS",8192,4.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","baichuan-m3-235b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-v100-32gb","beam-1-0-501b-a23b","cuda","no","Q8_0",8192,523.57,null,null,null,"over",null],["nvidia-tesla-v100-32gb","bielik-11b-v3-0-instruct","cuda","na","Q4_K_M",8192,9.44,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","bielik-minitron-7b-v3-0-instruct","cuda","na","Q4_K_M",8192,6.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","bitcpm-cann-3b-unquantized","cuda","na","IQ2_XXS",8192,2.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","caprl-qwen3vl-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","caprl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","cogito-671b-v2-1","cuda","no","Q2_K",8192,242.4,null,null,null,null,null],["nvidia-tesla-v100-32gb","command-a-plus-05-2026-bf16","cuda","no","IQ2_XXS",8192,63.63,null,null,null,null,null],["nvidia-tesla-v100-32gb","contextpilot-14b","cuda","na","IQ2_M",8192,8.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","contextpilot-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","contextpilot-e4b","cuda","na","Q2_K",8192,3.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","cosmos-reason2-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","cosmos-reason2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","d1-3b","cuda","na","Q4_K_M",8192,3.05,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1","cuda","no","Q2_K",8192,280.34,null,null,null,null,null],["nvidia-tesla-v100-32gb","deepseek-r1-0528-qwen3-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1-distill-llama-70b","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1-distill-llama-8b","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1-distill-qwen-14b","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1-distill-qwen-32b","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-r1-distill-qwen-7b","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","deepseek-v3","cuda","no","Q2_K",8192,257.8,null,null,null,null,null],["nvidia-tesla-v100-32gb","deepseek-v3-1","cuda","no","Q2_K",8192,242.41,null,null,null,null,null],["nvidia-tesla-v100-32gb","deepseek-v3-2","cuda","no","Q2_K",8192,242.08,null,null,null,null,null],["nvidia-tesla-v100-32gb","devstral-2-123b-instruct-2512","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-tesla-v100-32gb","devstral-small-2-24b-instruct-2512","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","eurollm-22b-2512","cuda","na","IQ2_XXS",8192,9.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","eurollm-22b-instruct-2512","cuda","na","IQ2_M",8192,10.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","eurollm-9b-instruct-2512","cuda","na","Q2_K",8192,6.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","euromoe-2-6b-a0-6b-instruct-2512","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","exaone-4-5-33b","cuda","na","IQ4_XS",8192,20.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","fara-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","fara1-5-27b","cuda","na","IQ2_M",8192,12.54,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","fara1-5-4b","cuda","na","IQ2_M",8192,3.76,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","fara1-5-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","frogboss-32b-2510","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","frogmini-14b-2510","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","frognano-4b-2609","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","functiongemma-270m-it","cuda","na","IQ4_XS",8192,1.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gelab-zero-4b-preview","cuda","na","IQ2_M",8192,3.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-2-27b-it","cuda","na","IQ2_M",8192,13.78,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-2-9b-it","cuda","na","IQ2_M",8192,7.67,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-3-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-3-1b-it","cuda","na","Q2_K",8192,2.31,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-3-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-3-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-12b","cuda","na","Q8_0",8192,15.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-12b-it","cuda","na","Q3_K_M",8192,8.73,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-26b-a4b","cuda","na","Q2_K",8192,13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-26b-a4b-it","cuda","na","IQ2_XXS",8192,12.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-31b","cuda","na","Q2_K",8192,17.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-31b-it","cuda","na","Q3_K_M",8192,20.34,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-e2b","cuda","na","Q2_K",8192,2.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-e2b-it","cuda","na","Q3_K_M",8192,2.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-e4b","cuda","na","Q2_K",8192,3.81,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","gemma-4-e4b-it","cuda","na","Q3_K_M",8192,4.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","glm-4-5","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-5-air","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-5-air-reap-82b-a12b","cuda","na","IQ2_XXS",8192,31.08,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","glm-4-6-reap-268b-a32b","cuda","no","Q2_K",8192,100.87,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-6v","cuda","no","Q2_K",8192,45.62,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-6v-flash","cuda","na","Q2_K",8192,5.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","glm-4-7","cuda","no","Q2_K",8192,130.74,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-7-flash","cuda","na","Q2_K",8192,12.77,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","glm-4-7-flash-reap-23b-a3b","cuda","na","Q2_K",8192,10.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","glm-4-7-reap-218b-a32b","cuda","no","Q2_K",8192,82.94,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-4-7-reap-268b-a32b","cuda","no","IQ2_XXS",8192,73.04,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-5","cuda","no","Q2_K",8192,268.86,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-5-1","cuda","no","IQ2_XXS",8192,197.58,null,null,null,null,null],["nvidia-tesla-v100-32gb","glm-5-2","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-tesla-v100-32gb","glm-5-3","cuda","no","Q8_0",8192,776.44,null,null,null,"over",null],["nvidia-tesla-v100-32gb","glm-5-3-flash","cuda","no","Q8_0",8192,327.9,null,null,null,"over",null],["nvidia-tesla-v100-32gb","glm-5-3-flash-bf16","cuda","no","IQ2_XXS",8192,91.96,null,null,null,null,null],["nvidia-tesla-v100-32gb","gpt-oss-120b","cuda","no","Q2_K",8192,62.76,null,null,null,null,null],["nvidia-tesla-v100-32gb","gpt-oss-20b","cuda","na","Q2_K",8192,12.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-3-3-8b-instruct","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-0-1b","cuda","na","Q2_K",8192,2.62,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-0-350m","cuda","na","Q2_K",8192,1.68,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-0-h-1b","cuda","na","Q2_K",8192,2.15,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-0-h-350m","cuda","na","Q2_K",8192,1.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-1-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-1-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-1-8b","cuda","na","Q3_K_M",8192,6.68,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-2-30b","cuda","na","Q2_K",8192,13.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-2-3b","cuda","na","Q2_K",8192,3.28,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-4-2-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-guardian-3-2-8b-factuality-detection","cuda","na","Q2_K",8192,5.64,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-guardian-4-0-3b-toxicity-ja","cuda","na","IQ2_XXS",8192,2.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-guardian-4-1-8b","cuda","na","Q2_K",8192,5.8,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","granite-vision-4-1-4b","cuda","na","Q4_K_M",8192,3.99,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","harc-llama-3-1-8b-instruct","cuda","na","IQ2_XXS",8192,4.51,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","harc-qwen2-5-7b-instruct","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","hermes-4-3-36b","cuda","na","IQ2_XXS",8192,12.89,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","hipo-1-7b","cuda","na","IQ2_XXS",8192,2.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo-3-1-0-8b","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo-3-1-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo-3-1-4b","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo-3-1-9b","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo2-235b-a22b","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-v100-32gb","holo2-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo2-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo2-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo3-35b-a3b","cuda","na","Q2_K",8192,14.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo4-27b","cuda","na","IQ2_XXS",8192,10.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holo4-35b-a3b","cuda","na","IQ2_XXS",8192,11.98,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","holotron4-30b-a3b","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","hunyuanocr","cuda","na","Q2_K",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","hy3","cuda","no","IQ2_XXS",8192,82.17,null,null,null,null,null],["nvidia-tesla-v100-32gb","intellect-3","cuda","no","IQ2_XXS",8192,39.58,null,null,null,null,null],["nvidia-tesla-v100-32gb","intent-aware-lfqa-llama3-8b-baseline","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-llama3-8b-intent-explicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-llama3-8b-intent-implicit","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-llama3-8b-multiview","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-4b-baseline","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-4b-intent-explicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-4b-intent-implicit","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-4b-multiview","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-8b-baseline","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-8b-intent-explicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-8b-intent-implicit","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intent-aware-lfqa-qwen3-8b-multiview","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","intern-s2-397b","cuda","no","IQ2_XXS",8192,114.31,null,null,null,null,null],["nvidia-tesla-v100-32gb","ising-calibration-1-35b-a3b","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ising-calibration-1-5-31b-bf16","cuda","na","IQ2_XXS",8192,16.51,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","januscoder-14b","cuda","na","Q2_K",8192,8.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","januscoder-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","januscoderv-7b","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","k-exaone-236b-a23b","cuda","no","IQ4_XS",8192,126.29,null,null,null,null,null],["nvidia-tesla-v100-32gb","kanana-2-3b-base","cuda","na","IQ2_XXS",8192,3.31,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kanana-2-3b-instruct","cuda","na","Q2_K",8192,3.63,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kat-coder-v2-5-dev","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kat-dev-72b-exp","cuda","na","IQ2_XXS",8192,28.54,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kimi-k2-5","cuda","no","Q2_K",8192,367.95,null,null,null,"over",null],["nvidia-tesla-v100-32gb","kimi-k2-6","cuda","no","IQ2_XXS",8192,267.64,null,null,null,null,null],["nvidia-tesla-v100-32gb","kimi-k2-instruct","cuda","no","Q2_K",8192,367.37,null,null,null,"over",null],["nvidia-tesla-v100-32gb","kimi-k2-thinking","cuda","no","Q2_K",8192,368.29,null,null,null,"over",null],["nvidia-tesla-v100-32gb","kimi-linear-48b-a3b-base","cuda","na","IQ2_XXS",8192,14.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kimi-linear-48b-a3b-instruct","cuda","na","IQ2_XXS",8192,13.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","kimi-linear-reap-35b-a3b-instruct","cuda","na","IQ2_XXS",8192,10.67,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","laguna-s-2-1","cuda","no","Q4_K_M",8192,95.87,null,null,null,null,null],["nvidia-tesla-v100-32gb","laguna-xs-2-1","cuda","na","IQ2_XXS",8192,11.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-2-6b-exp","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-2-6b-longevity","cuda","na","Q2_K",8192,2.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-2-6b-transcript","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-24b-a2b","cuda","na","Q4_0",8192,14.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-1-2b-base","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-1-2b-instruct","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-1-2b-jp","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-1-2b-jp-202606","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-1-2b-thinking","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-2-6b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-2-6b-base","cuda","na","IQ2_XXS",8192,2.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-230m","cuda","na","Q4_0",8192,1.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-24b-a2b","cuda","na","Q4_0",8192,14.75,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-350m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-8b-a1b","cuda","na","Q4_0",8192,6.12,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-encoder-350m-diffusion","cuda","na","IQ2_XXS",8192,1.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-vl-1-6b","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-vl-1-6b-extract","cuda","na","Q4_0",8192,2.06,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-vl-3b","cuda","na","Q4_0",8192,2.97,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-vl-450m","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-5-vl-450m-extract","cuda","na","Q4_0",8192,1.59,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-8b-a1b","cuda","na","Q4_0",8192,6.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","lfm2-vl-3b","cuda","na","Q4_0",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ling-1t","cuda","no","Q2_K",8192,360.62,null,null,null,"over",null],["nvidia-tesla-v100-32gb","llama-3-1-70b-instruct","cuda","na","IQ2_XXS",8192,22.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","llama-3-1-8b-instruct","cuda","na","Q2_K",8192,5.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","llama-3-2-1b-instruct","cuda","na","Q2_K",8192,2.1,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","llama-3-2-3b-instruct","cuda","na","Q2_K",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","llama-3-3-70b-instruct","cuda","na","Q2_K",8192,29.42,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","llama-4-scout-17b-16e-instruct","cuda","no","Q2_K",8192,41.46,null,null,null,null,null],["nvidia-tesla-v100-32gb","mathform-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","medgemma-1-5-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-1-12b-a2-5b-thinking","cuda","na","Q4_K_M",8192,9.38,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-12b-a2-5b-base","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-12b-a2-5b-instruct","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-12b-a2-5b-instruct-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-12b-a2-5b-thinking","cuda","na","IQ2_M",8192,6.5,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mellum2-12b-a2-5b-thinking-sft","cuda","na","IQ2_XXS",8192,5.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mimo-embodied-7b","cuda","na","IQ2_XXS",8192,4.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mimo-v2-5","cuda","no","IQ2_XXS",8192,82.44,null,null,null,null,null],["nvidia-tesla-v100-32gb","mimo-v2-5-pro","cuda","no","IQ2_XXS",8192,270.42,null,null,null,null,null],["nvidia-tesla-v100-32gb","mimo-v2-6-distill-qwen-9b","cuda","na","IQ2_M",8192,5.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mimo-v2-6-flash-mopd","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-tesla-v100-32gb","mimo-v2-6-flash-rl","cuda","no","Q2_K",8192,124.94,null,null,null,null,null],["nvidia-tesla-v100-32gb","mimo-v2-6-pro-mopd","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-tesla-v100-32gb","mimo-v2-6-pro-rl","cuda","no","Q2_K",8192,411.6,null,null,null,"over",null],["nvidia-tesla-v100-32gb","mimo-v2-flash","cuda","no","Q2_K",8192,111.57,null,null,null,null,null],["nvidia-tesla-v100-32gb","minicpm-o-4-5","cuda","na","Q4_0",8192,6.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm-v-4-6","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm-v-4-6-thinking","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm-v-4-7-1b","cuda","na","Q4_0",8192,2.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm-v-4-7-35b-a3b","cuda","na","IQ4_XS",8192,20.02,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm5-1b","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm5-1b-base","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm5-1b-sft","cuda","na","IQ2_XXS",8192,1.79,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm5-2b","cuda","na","IQ2_M",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minicpm5-2b-base","cuda","na","IQ2_XXS",8192,2.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","minimax-m2","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-v100-32gb","minimax-m2-1","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-v100-32gb","minimax-m2-5","cuda","no","Q2_K",8192,84.92,null,null,null,null,null],["nvidia-tesla-v100-32gb","minimax-m2-5-reap-139b-a10b","cuda","no","IQ2_XXS",8192,39.25,null,null,null,null,null],["nvidia-tesla-v100-32gb","minimax-m2-7","cuda","no","IQ2_XXS",8192,62.9,null,null,null,null,null],["nvidia-tesla-v100-32gb","ministral-3-14b-instruct-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ministral-3-14b-reasoning-2512","cuda","na","Q4_K_M",8192,10.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ministral-3-3b-instruct-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ministral-3-3b-reasoning-2512","cuda","na","Q4_K_M",8192,4.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ministral-3-8b-instruct-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ministral-3-8b-reasoning-2512","cuda","na","Q4_K_M",8192,7.19,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mistral-7b-instruct-v0-2","cuda","na","IQ2_XXS",8192,4.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mistral-large-3-675b-instruct-2512","cuda","no","Q2_K",8192,243.79,null,null,null,null,null],["nvidia-tesla-v100-32gb","mistral-medium-3-5-128b","cuda","no","Q2_K",8192,49.32,null,null,null,null,null],["nvidia-tesla-v100-32gb","mistral-nemo-instruct-2407","cuda","na","IQ2_M",8192,6.65,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mistral-small-3-2-24b-instruct-2506","cuda","na","Q2_K",8192,11.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","mistral-small-4-119b-2603","cuda","na","IQ2_XXS",8192,34.29,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","muse-glimmer-30b","cuda","na","IQ2_XXS",8192,10.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","muse-spark-open-816b-a42b","cuda","no","Q2_K",8192,301.03,null,null,null,"over",null],["nvidia-tesla-v100-32gb","nemotron-3-content-safety","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-3-nano-omni-30b-a3b-reasoning-bf16","cuda","na","Q4_K_M",8192,23.26,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-cascade-14b-thinking","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-cascade-2-30b-a3b","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-cascade-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-cascade-8b-thinking","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-orchestrator-8b","cuda","na","IQ2_M",8192,5.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-terminal-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-terminal-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nemotron-terminal-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","north-mini-code-1-0","cuda","na","IQ2_XXS",8192,10.7,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nouscoder-14b","cuda","na","IQ2_M",8192,7.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-5-lightning-30b-a3b-base-bf16","cuda","na","Q2_K",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-5-lightning-30b-a3b-bf16","cuda","na","IQ2_M",8192,19.07,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-5-super-vl-120b-a12b-bf16","cuda","no","Q4_0",8192,71.85,null,null,null,null,null],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-nano-30b-a3b-bf16","cuda","na","IQ4_XS",8192,19.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-nano-4b-bf16","cuda","na","Q3_K_M",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-super-120b-a12b-base-bf16","cuda","no","IQ2_XXS",8192,49.78,null,null,null,null,null],["nvidia-tesla-v100-32gb","nvidia-nemotron-3-super-120b-a12b-bf16","cuda","no","IQ2_XXS",8192,51.01,null,null,null,null,null],["nvidia-tesla-v100-32gb","nvidia-nemotron-labs-3-elastic-30b-a3b-bf16","cuda","na","IQ2_M",8192,18.88,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","nvidia-nemotron-nano-9b-v2","cuda","na","IQ2_M",8192,6.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1-32b-instruct","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1-32b-instruct-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1-7b-rl-zero-math","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-1125-32b","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-32b-think","cuda","na","Q2_K",8192,15,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-32b-think-dpo","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-32b-think-sft","cuda","na","IQ2_XXS",8192,11.82,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-instruct","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-instruct-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-instruct-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-rl-zero-code","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-rl-zero-general","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-rl-zero-if","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-rl-zero-math","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-rl-zero-mix","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-think","cuda","na","Q2_K",8192,8.17,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-think-dpo","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmo-3-7b-think-sft","cuda","na","IQ2_XXS",8192,7.47,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","olmocr-2-7b-1025","cuda","na","IQ2_M",8192,4.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","optimind-sft","cuda","na","IQ2_M",8192,13.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","phi-3-5-mini-instruct","cuda","na","IQ2_M",8192,5.69,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","phi-4","cuda","na","Q2_K",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","phi-4-mini-instruct","cuda","na","Q2_K",8192,4.11,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen-agentworld-35b-a3b","cuda","na","Q8_0",8192,37.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-14b-instruct","cuda","na","Q2_K",8192,8.3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-3b-instruct","cuda","na","Q2_K",8192,2.86,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-72b-instruct","cuda","na","Q2_K",8192,30.34,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-coder-32b-instruct","cuda","na","Q2_K",8192,15.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-coder-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-vl-7b-instruct","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen2-5-vl-7b-surg-cholect50","cuda","na","Q2_K",8192,4.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-0-6b","cuda","na","Q4_0",8192,2.57,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-1-7b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-14b","cuda","na","Q4_K_M",8192,11.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-235b-a22b","cuda","no","Q4_K_M",8192,141.88,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-235b-a22b-instruct-2507","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-30b-a3b","cuda","na","Q4_K_M",8192,20.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-30b-a3b-instruct-2507","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-32b","cuda","na","Q4_K_M",8192,22.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-4b","cuda","na","Q4_K_M",8192,4.95,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-4b-instruct-2507","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-0-8b","cuda","na","Q3_K_M",8192,2.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-0-8b-base","cuda","na","IQ2_XXS",8192,2.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-122b-a10b","cuda","na","IQ2_XXS",8192,35.03,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-27b","cuda","na","Q3_K_M",8192,15.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-2b","cuda","na","Q3_K_M",8192,2.77,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-2b-base","cuda","na","IQ2_XXS",8192,2.46,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-35b-a3b","cuda","na","Q3_K_M",8192,17.55,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-35b-a3b-base","cuda","na","IQ2_XXS",8192,10.92,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-397b-a17b","cuda","no","Q3_K_M",8192,175.62,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-5-4b","cuda","na","Q3_K_M",8192,4.22,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-4b-base","cuda","na","Q2_K",8192,3.85,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-9b","cuda","na","Q3_K_M",8192,6.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-5-9b-base","cuda","na","Q2_K",8192,5.4,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-6-27b","cuda","na","Q3_K_M",8192,15.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-6-35b-a3b","cuda","na","IQ2_XXS",8192,11.35,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-8-2-4t-a95b","cuda","no","Q8_0",8192,2524.12,null,null,null,"over",null],["nvidia-tesla-v100-32gb","qwen3-8-27b","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-8-3-6-27b-blend","cuda","na","IQ2_XXS",8192,10.58,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-8b","cuda","na","Q4_K_M",8192,7.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-coder-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-coder-480b-a35b-instruct","cuda","no","Q2_K",8192,174.28,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-coder-next","cuda","na","Q2_K",8192,30.37,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-coder-next-base","cuda","na","IQ2_XXS",8192,22.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-coder-reap-25b-a3b","cuda","na","IQ2_XXS",8192,8.11,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-coder-reap-363b-a35b","cuda","no","Q2_K",8192,132.69,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-nemotron-14b-brrm","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-nemotron-235b-a22b-genrm","cuda","no","IQ2_XXS",8192,63.24,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-nemotron-8b-brrm","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-next-80b-a3b-instruct","cuda","na","Q2_K",8192,30.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-235b-a22b-instruct","cuda","no","Q2_K",8192,86.67,null,null,null,null,null],["nvidia-tesla-v100-32gb","qwen3-vl-2b-instruct","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-2b-thinking","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-30b-a3b-instruct","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-32b-instruct","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-32b-thinking","cuda","na","Q2_K",8192,15.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-4b-instruct","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-4b-thinking","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-8b-instruct","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwen3-vl-8b-thinking","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","qwq-32b","cuda","na","Q4_K_M",8192,22.45,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","riva-translate-4b-instruct-v1-1","cuda","na","IQ2_XXS",8192,3.93,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","rlvr-8b-0926","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","rnj-1-instruct","cuda","na","Q2_K",8192,5.56,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","sera-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","singguard-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","smollm3-3b","cuda","na","Q2_K",8192,3.09,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","smollm3-3b-gsm8k-sft","cuda","na","IQ2_XXS",8192,2.78,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","solar-open-100b","cuda","na","IQ2_XXS",8192,29.36,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","spatial-ssrl-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","spatial-ssrl-qwen3vl-4b","cuda","na","Q2_K",8192,4.14,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","step-3-5-flash","cuda","no","IQ2_XXS",8192,48.93,null,null,null,null,null],["nvidia-tesla-v100-32gb","step-3-5-flash-reap-121b-a11b","cuda","na","IQ2_XXS",8192,32.92,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","step-3-5-flash-reap-149b-a11b","cuda","no","IQ2_XXS",8192,40.14,null,null,null,null,null],["nvidia-tesla-v100-32gb","step-3-7-flash","cuda","no","IQ3_XXS",8192,76.06,null,null,null,null,null],["nvidia-tesla-v100-32gb","step3-vl-10b-base","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","tiny-aya-earth","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","tiny-aya-fire","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","tiny-aya-global","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","tiny-aya-water","cuda","na","Q4_0",8192,4.13,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","translategemma-12b-it","cuda","na","Q2_K",8192,8.23,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","translategemma-27b-it","cuda","na","Q2_K",8192,14.43,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","translategemma-4b-it","cuda","na","Q2_K",8192,3.94,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-large-base","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-tesla-v100-32gb","trinity-large-thinking","cuda","no","IQ2_XXS",8192,107.1,null,null,null,null,null],["nvidia-tesla-v100-32gb","trinity-large-truebase","cuda","no","IQ2_XXS",8192,96.44,null,null,null,null,null],["nvidia-tesla-v100-32gb","trinity-mini","cuda","na","IQ2_XXS",8192,8.25,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-mini-base","cuda","na","IQ2_XXS",8192,8.69,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-mini-base-pre-anneal","cuda","na","IQ2_XXS",4096,8.41,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-nano-base","cuda","na","IQ2_XXS",8192,3.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-nano-base-pre-anneal","cuda","na","IQ2_XXS",4096,3.27,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","trinity-nano-preview","cuda","na","IQ2_M",8192,3.84,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-mate-27b","cuda","na","IQ2_XXS",8192,11.21,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-mate-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-mate-democua-27b","cuda","na","Q2_K",8192,12.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-venus-1-5-2b","cuda","na","Q2_K",8192,3,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-venus-1-5-30b-a3b","cuda","na","Q2_K",8192,13.04,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-venus-1-5-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","ui-venus-2-9b","cuda","na","IQ2_M",8192,5.24,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","userrepgen-4b","cuda","na","IQ2_M",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","webworld-14b","cuda","na","IQ2_XXS",8192,6.6,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","webworld-32b","cuda","na","IQ2_XXS",8192,12.01,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","webworld-8b","cuda","na","Q2_K",8192,5.52,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","x-reasoner-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","youtu-llm-2b","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","youtu-llm-2b-base","cuda","na","IQ2_XXS",8192,2.2,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","youtu-vl-4b-instruct","cuda","na","IQ2_XXS",8192,3.53,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","zwz-2b","cuda","na","Q4_K_M",8192,3.32,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","zwz-4b","cuda","na","IQ2_XXS",8192,3.72,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","zwz-7b","cuda","na","IQ2_XXS",8192,3.83,null,null,null,null,"no_measured_total"],["nvidia-tesla-v100-32gb","zwz-8b","cuda","na","IQ2_XXS",8192,4.74,null,null,null,null,"no_measured_total"]]}