DeskGPU
English

NVIDIA GeForce RTX 3090 Ti: which LLMs can it run?

This page was written and translated automatically by AI and checked by software against its sources, with no human editing. Specifications come from the sources listed; memory requirements and speeds are estimates calculated with published formulas. How we use AI

NVIDIA GeForce RTX 3090 Ti has 24 GB of memory (manufacturer figure). Below, every model in the database is checked against it with llama.cpp at a context length of 8,192 tokens (or the model’s maximum if shorter).

Values updated Oct 19, 2026

Specifications

Memory (manufacturer figure)
24 GB
Memory type
GDDR6X
Memory bus width
384 bit
Memory bandwidth
1,008 GB/s
Board power (TDP)
450 W
FP16 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
BF16 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
FP8 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
FP4 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
INT8 tensor, dense
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.
Interface
Not shown: open sources do not give two independent, agreeing values with a manufacturer reference.

Each value lists every source with its own figure; units have been normalized. A manufacturer’s “GB” of GPU memory is counted as GiB (2³⁰ bytes), which is also how AMD’s ROCm table states it. How specifications are checked

Run profile

Run profile: llama.cpp, CUDA back end (NVIDIA discrete GPU), all layers on the GPU, Flash Attention on, micro-batch (-ub) 512, F16 KV cache, context (-c) as shown; “Fits” is judged with llama-server’s default 4 parallel sequences (-np auto, unified KV cache) and “Doesn’t fit” with 1 sequence; idle GPU with no other programs using its memory.

Memory counted as available for “Fits” (C_low): 20.88 GiB per card = 24 GiB nominal − 1,054 MiB (the largest gap between nominal and reported total measured on consumer and workstation GPUs in this profile, used because no public log reports this GPU’s own total) − 2,112 MiB (the largest start-up and runtime use seen in this profile’s public logs), rounded down to a multiple of 64 MiB.

These results assume the card’s default configuration. Settings that reduce usable memory (for example ECC, where the card supports it) are not covered.

Memory used for “Doesn’t fit” (C_high): the full 24 GiB per card. Run profiles and their measurements

Which models fit

“Fits” means llama.cpp's default --fit load check would place all layers on the GPU: our estimate of llama.cpp's buffers, plus its error margin, plus llama.cpp's 1 GiB per-card reserve, is within the memory counted as available. It does not promise that peak memory while generating fits. How results are decided

Context 8,192 tokens (or the model’s maximum if shorter). The last columns show the longest context at that quantization and the bandwidth-based speed ceiling.
Model Parameters Highest quantization that fits Available memory needed for “Fits” Longest context Speed ceiling Result
AI21-Jamba2-Mini 51.6B (11.8B active) Q2_K 19.0 GiB 111,104 ≤ 229 tok/s Fits
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) IQ3_XXS 20.0 GiB 92,416 ≤ 710 tok/s Fits
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) IQ3_XXS 20.7 GiB 27,136 ≤ 586 tok/s Fits
Hermes-4.3-36B 36.2B Q3_K_M 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) IQ4_XS 19.8 GiB 112,896 ≤ 540 tok/s Fits
Holo-3.1-35B-A3B 34.7B (2.9B active) IQ4_XS 20.2 GiB 37,376 ≤ 493 tok/s Fits
Holo3-35B-A3B 34.7B (2.9B active) IQ4_XS 20.2 GiB 37,376 ≤ 493 tok/s Fits
Holo4-35B-A3B 34.7B (2.9B active) Q3_K_M 18.4 GiB 120,064 ≤ 383 tok/s Fits
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB 46,592 ≤ 495 tok/s Fits
KAT-Coder-V2.5-Dev 34.7B (2.9B active) IQ4_XS 20.1 GiB 43,264 ≤ 477 tok/s Fits
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB 158,464 ≤ 387 tok/s Fits
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) IQ4_XS 19.9 GiB 50,176 ≤ 515 tok/s Fits
Qwen3.6-35B-A3B 34.7B (2.9B active) IQ4_XS 20.1 GiB 43,520 ≤ 478 tok/s Fits
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB 46,592 ≤ 495 tok/s Fits
Laguna-XS-2.1 33.4B (2.8B active) Q4_0 20.6 GiB 13,824 ≤ 436 tok/s Fits
DeepSeek-R1-Distill-Qwen-32B 32.8B Q3_K_M 18.7 GiB 16,384 ≤ 56.8 tok/s Fits
Qwen2.5-32B-Instruct 32.8B Q3_K_M 18.7 GiB 16,384 ≤ 56.8 tok/s Fits
Qwen2.5-Coder-32B-Instruct 32.8B Q3_K_M 18.7 GiB 16,384 ≤ 56.8 tok/s Fits
AesCode-32B 32.8B IQ4_XS 20.8 GiB 8,448 ≤ 50.8 tok/s Fits
Cosmos-Reason2-32B 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
FrogBoss-32B-2510 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
Nemotron-Terminal-32B 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
Qwen3-VL-32B-Instruct 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
Qwen3-VL-32B-Thinking 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
SERA-32B 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
WebWorld-32B 32.8B IQ4_XS 20.4 GiB 9,984 ≤ 51.9 tok/s Fits
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB 9,728 ≤ 54.0 tok/s Fits
Olmo-3.1-32B-Instruct 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3.1-32B-Instruct-DPO 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3.1-32B-Think 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3-1125-32B 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3-32B-Think 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3-32B-Think-DPO 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Olmo-3-32B-Think-SFT 32.2B IQ4_XS 20.1 GiB 11,008 ≤ 54.8 tok/s Fits
Holotron4-30B-A3B 31.6B (3.2B active) Q4_0 19.0 GiB 238,336 ≤ 485 tok/s Fits
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) Q4_0 19.2 GiB 212,224 ≤ 440 tok/s Fits
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q4_0 19.0 GiB 238,336 ≤ 485 tok/s Fits
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.3 GiB 207,360 ≤ 439 tok/s Fits
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.2 GiB 219,136 ≤ 451 tok/s Fits
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.0 GiB 238,336 ≤ 485 tok/s Fits
gemma-4-31B 30.7B Q2_K 17.6 GiB 48,128 ≤ 75.2 tok/s Fits
gemma-4-31B-it 30.7B Q3_K_M 20.3 GiB 14,592 ≤ 62.1 tok/s Fits
Ising-Calibration-1.5-31B-BF16 30.7B IQ3_XXS 18.6 GiB 35,328 ≤ 69.6 tok/s Fits
Holo2-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 15,616 ≤ 370 tok/s Fits
North-Mini-Code-1.0 30.5B (3.3B active) Q4_K_M 20.7 GiB 9,472 ≤ 360 tok/s Fits
GLM-4.7-Flash 29.9B (3.6B active) Q4_K_M 19.5 GiB 32,512 ≤ 354 tok/s Fits
granite-4.2-30b 29.3B Q4_K_M 20.5 GiB 9,472 ≤ 51.3 tok/s Fits
granite-4.1-30b 28.9B Q4_K_M 20.5 GiB 9,472 ≤ 51.3 tok/s Fits
Muse-Glimmer-30B 27.9B Q5_K_M 20.7 GiB 21,248 ≤ 52.1 tok/s Fits
gemma-2-27b-it 27.2B IQ4_XS 19.1 GiB 8,192 ≤ 58.9 tok/s Fits
gemma-3-27b-it 27.0B Q4_K_M 20.3 GiB 14,336 ≤ 57.1 tok/s Fits
translategemma-27b-it 27.0B Q4_K_M 20.3 GiB 14,336 ≤ 57.1 tok/s Fits
Fara1.5-27B 26.9B Q4_K_M 19.1 GiB 34,304 ≤ 58.1 tok/s Fits
Holo4-27B 26.9B Q5_K_M 20.6 GiB 11,520 ≤ 53.4 tok/s Fits
Qwen3.5-27B 26.9B Q4_K_M 18.4 GiB 46,080 ≤ 60.9 tok/s Fits
Qwen3.6-27B 26.9B Q4_K_M 18.4 GiB 45,056 ≤ 60.6 tok/s Fits
Qwen3.8-27B 26.9B Q4_K_M 18.8 GiB 39,168 ≤ 59.2 tok/s Fits
Qwen3.8-3.6-27B-blend 26.9B Q4_K_M 18.8 GiB 39,168 ≤ 59.2 tok/s Fits
UI-Mate-27B 26.9B Q4_K_M 19.1 GiB 34,304 ≤ 58.1 tok/s Fits
UI-Mate-democua-27B 26.9B Q5_K_M 20.6 GiB 11,520 ≤ 53.4 tok/s Fits
Trinity-Mini 26.1B (3.1B active) Q5_K_M 19.9 GiB 57,856 ≤ 396 tok/s Fits
Trinity-Mini-Base 26.1B (3.1B active) Q5_K_M 19.9 GiB 62,208 ≤ 409 tok/s Fits
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) Q5_K_M 19.6 GiB 4,096 ≤ 421 tok/s Fits
gemma-4-26B-A4B 25.2B (3.8B active) Q4_K_M 19.1 GiB 88,832 ≤ 339 tok/s Fits
gemma-4-26B-A4B-it 25.2B (3.8B active) Q4_K_M 19.3 GiB 78,080 ≤ 314 tok/s Fits
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) Q5_K_M 19.3 GiB 24,320 ≤ 332 tok/s Fits
LFM2.5-24B-A2B 24.0B (2.5B active) Q6_K 20.7 GiB 14,080 ≤ 459 tok/s Fits
LFM2-24B-A2B 23.8B (2.3B active) Q6_K 20.6 GiB 18,944 ≤ 481 tok/s Fits
Devstral-Small-2-24B-Instruct-2512 23.6B Q5_K_M 18.6 GiB 22,272 ≤ 57.2 tok/s Fits
Mistral-Small-3.2-24B-Instruct-2506 23.6B Q5_K_M 18.6 GiB 22,272 ≤ 57.2 tok/s Fits
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q6_K 20.1 GiB 21,760 ≤ 288 tok/s Fits
EuroLLM-22B-2512 22.6B Q6_K 20.6 GiB 9,216 ≤ 51.1 tok/s Fits
EuroLLM-22B-Instruct-2512 22.6B Q6_K 20.6 GiB 9,216 ≤ 51.1 tok/s Fits
gpt-oss-20b 20.9B (3.6B active) Q8_0 12.9 GiB 131,072 ≤ 363 tok/s Fits
OptiMind-SFT 20.9B (3.6B active) Q5_K_M 17.8 GiB 127,232 ≤ 314 tok/s Fits
DeepSeek-R1-Distill-Qwen-14B 14.8B Q8_0 17.5 GiB 25,600 ≤ 61.2 tok/s Fits
Qwen2.5-14B-Instruct 14.8B Q8_0 17.5 GiB 25,600 ≤ 61.2 tok/s Fits
ContextPilot-14B 14.8B Q8_0 17.2 GiB 30,720 ≤ 62.2 tok/s Fits
FrogMini-14B-2510 14.8B Q6_K 13.9 GiB 40,960 ≤ 78.6 tok/s Fits
JanusCoder-14B 14.8B Q8_0 17.2 GiB 30,720 ≤ 62.2 tok/s Fits
Nemotron-Cascade-14B-Thinking 14.8B Q8_0 17.2 GiB 30,720 ≤ 62.2 tok/s Fits
Nemotron-Terminal-14B 14.8B Q6_K 13.9 GiB 40,960 ≤ 78.6 tok/s Fits
NousCoder-14B 14.8B Q8_0 17.2 GiB 30,720 ≤ 62.2 tok/s Fits
Qwen3-14B 14.8B Q8_0 17.2 GiB 30,720 ≤ 62.2 tok/s Fits
Qwen3-Nemotron-14B-BRRM 14.8B Q6_K 13.9 GiB 40,960 ≤ 78.6 tok/s Fits
WebWorld-14B 14.8B Q6_K 13.9 GiB 40,960 ≤ 78.6 tok/s Fits
phi-4 14.7B Q8_0 17.7 GiB 16,384 ≤ 60.3 tok/s Fits
Apriel-1.6-15b-Thinker 14.4B Q8_0 17.2 GiB 26,880 ≤ 62.1 tok/s Fits
Ministral-3-14B-Instruct-2512 13.5B Q8_0 16.0 GiB 38,144 ≤ 67.3 tok/s Fits
Ministral-3-14B-Reasoning-2512 13.5B Q8_0 16.0 GiB 38,144 ≤ 67.3 tok/s Fits
Mistral-Nemo-Instruct-2407 12.2B Q8_0 14.7 GiB 46,336 ≤ 73.9 tok/s Fits
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 399 tok/s Fits
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 480 tok/s Fits
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 399 tok/s Fits
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 480 tok/s Fits
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 399 tok/s Fits
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 480 tok/s Fits
gemma-4-12B 11.9B Q8_0 15.6 GiB 262,144 ≤ 76.8 tok/s Fits
gemma-4-12B-it 11.9B Q8_0 15.6 GiB 262,144 ≤ 76.8 tok/s Fits
gemma-3-12b-it 11.8B Q8_0 15.8 GiB 84,480 ≤ 75.4 tok/s Fits
translategemma-12b-it 11.8B Q8_0 15.8 GiB 84,480 ≤ 75.4 tok/s Fits
Bielik-11B-v3.0-Instruct 11.2B Q8_0 14.4 GiB 32,768 ≤ 75.2 tok/s Fits
AutoGLM-Phone-9B 9.4B F16 18.9 GiB 55,808 ≤ 56.3 tok/s Fits
AutoGLM-Phone-9B-Multilingual 9.4B Q6_K 9.2 GiB 65,536 ≤ 125 tok/s Fits
GLM-4.6V-Flash 9.4B BF16 18.9 GiB 55,808 ≤ 56.3 tok/s Fits
gemma-2-9b-it 9.2B Q8_0 14.8 GiB 8,192 ≤ 78.8 tok/s Fits
EuroLLM-9B-Instruct-2512 9.2B F16 19.6 GiB 15,616 ≤ 54.0 tok/s Fits
Fara1.5-9B 9.0B BF16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
Holo-3.1-9B 9.0B F16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
MiMo-V2.6-Distill-Qwen-9B 9.0B BF16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
Qwen3.5-9B 9.0B BF16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
Qwen3.5-9B-Base 9.0B F16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
UI-Mate-9B 9.0B BF16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
UI-Venus-2-9B 9.0B BF16 17.5 GiB 105,472 ≤ 62.4 tok/s Fits
NVIDIA-Nemotron-Nano-9B-v2 8.9B BF16 18.3 GiB 131,072 ≤ 60.2 tok/s Fits
granite-4.1-8b 8.8B BF16 19.0 GiB 19,456 ≤ 55.7 tok/s Fits
granite-4.2-8b 8.8B BF16 19.0 GiB 19,456 ≤ 55.7 tok/s Fits
Ministral-3-8B-Instruct-2512 8.5B BF16 18.0 GiB 28,928 ≤ 59.1 tok/s Fits
Ministral-3-8B-Reasoning-2512 8.5B BF16 18.0 GiB 28,928 ≤ 59.1 tok/s Fits
LFM2.5-8B-A1B 8.5B (1.7B active) BF16 18.0 GiB 128,000 ≤ 290 tok/s Fits
granite-guardian-4.1-8b 8.4B BF16 19.0 GiB 19,456 ≤ 55.7 tok/s Fits
LFM2-8B-A1B 8.3B (1.6B active) F16 17.7 GiB 128,000 ≤ 313 tok/s Fits
rnj-1-instruct 8.3B BF16 18.6 GiB 25,344 ≤ 57.0 tok/s Fits
AesCode-8B 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
ArmorOCR 8.2B Q8_0 10.4 GiB 79,616 ≤ 109 tok/s Fits
AstaBrief_8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 136 tok/s Fits
ContextPilot-8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 136 tok/s Fits
Cosmos-Reason2-8B 8.2B Q6_K 8.6 GiB 91,904 ≤ 136 tok/s Fits
DeepSeek-R1-0528-Qwen3-8B 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Holo2-8B 8.2B Q6_K 8.6 GiB 91,904 ≤ 136 tok/s Fits
intent-aware-lfqa-qwen3-8b-baseline 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
intent-aware-lfqa-qwen3-8b-multiview 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
JanusCoder-8B 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
MathForm-8B 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Nemotron-Cascade-8B 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Nemotron-Cascade-8B-Thinking 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Nemotron-Orchestrator-8B 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Nemotron-Terminal-8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 136 tok/s Fits
Qwen3-8B 8.2B Q8_0 10.4 GiB 40,960 ≤ 109 tok/s Fits
Qwen3-Nemotron-8B-BRRM 8.2B Q6_K 8.6 GiB 40,960 ≤ 136 tok/s Fits
Qwen3-VL-8B-Instruct 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
Qwen3-VL-8B-Thinking 8.2B BF16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
RLVR-8B-0926 8.2B Q6_K 8.6 GiB 91,904 ≤ 136 tok/s Fits
Step3-VL-10B-Base 8.2B Q6_K 8.6 GiB 40,960 ≤ 136 tok/s Fits
UI-Venus-1.5-8B 8.2B Q6_K 8.6 GiB 91,904 ≤ 136 tok/s Fits
WebWorld-8B 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
ZwZ-8B 8.2B Q6_K 8.6 GiB 91,904 ≤ 136 tok/s Fits
MiniCPM-o-4_5 8.2B F16 17.3 GiB 32,256 ≤ 61.7 tok/s Fits
granite-3.3-8b-instruct 8.2B F16 18.6 GiB 22,016 ≤ 57.0 tok/s Fits
granite-guardian-3.2-8b-factuality-detection 8.2B F16 18.6 GiB 22,016 ≤ 57.0 tok/s Fits
intent-aware-lfqa-llama3-8b-baseline 8.0B F16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B F16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B F16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
intent-aware-lfqa-llama3-8b-multiview 8.0B F16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
DeepSeek-R1-Distill-Llama-8B 8.0B BF16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
HARC-Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 103,936 ≤ 139 tok/s Fits
Llama-3.1-8B-Instruct 8.0B BF16 17.0 GiB 37,376 ≤ 62.7 tok/s Fits
AprielGuard 7.9B Q6_K 7.9 GiB 131,072 ≤ 150 tok/s Fits
MiMo-Embodied-7B 7.6B Q6_K 8.1 GiB 94,976 ≤ 145 tok/s Fits
DeepSeek-R1-Distill-Qwen-7B 7.6B F16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
Fara-7B 7.6B BF16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
HARC-Qwen2.5-7B-Instruct 7.6B Q6_K 7.5 GiB 32,768 ≤ 161 tok/s Fits
JanusCoderV-7B 7.6B BF16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
olmOCR-2-7B-1025 7.6B BF16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
Qwen2.5-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 126 tok/s Fits
Qwen2.5-Coder-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 126 tok/s Fits
Qwen2.5-VL-7B-Instruct 7.6B BF16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
Qwen2.5-VL-7B-Surg-CholecT50 7.6B F16 15.6 GiB 97,792 ≤ 69.0 tok/s Fits
Spatial-SSRL-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 161 tok/s Fits
X-Reasoner-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 161 tok/s Fits
ZwZ-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 161 tok/s Fits
gemma-4-E4B 7.5B F16 11.0 GiB 131,072 ≤ 105 tok/s Fits
gemma-4-E4B-it 7.5B BF16 11.0 GiB 131,072 ≤ 105 tok/s Fits
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q8_0 10.2 GiB 32,768 ≤ 110 tok/s Fits
ContextPilot-E4B 7.5B F16 10.9 GiB 131,072 ≤ 107 tok/s Fits
Olmo-3.1-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3.1-7B-RL-Zero-Math 7.3B F16 19.0 GiB 11,776 ≤ 61.2 tok/s Fits
Olmo-3-7B-Instruct 7.3B BF16 19.0 GiB 11,776 ≤ 61.2 tok/s Fits
Olmo-3-7B-Instruct-DPO 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-Instruct-SFT 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-RL-Zero-General 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-RL-Zero-IF 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-RL-Zero-Math 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-RL-Zero-Mix 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-Think 7.3B BF16 19.0 GiB 11,776 ≤ 61.2 tok/s Fits
Olmo-3-7B-Think-DPO 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Olmo-3-7B-Think-SFT 7.3B Q6_K 11.0 GiB 57,600 ≤ 121 tok/s Fits
Mistral-7B-Instruct-v0.2 7.2B Q6_K 8.1 GiB 32,768 ≤ 146 tok/s Fits
Trinity-Nano-Base 6.1B (819M active) Q6_K 6.7 GiB 131,072 ≤ 1,119 tok/s Fits
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) Q6_K 6.4 GiB 4,096 ≤ 1,197 tok/s Fits
Trinity-Nano-Preview 6.1B (819M active) BF16 13.5 GiB 131,072 ≤ 543 tok/s Fits
Youtu-VL-4B-Instruct 4.9B Q6_K 5.9 GiB 32,768 ≤ 228 tok/s Fits
Holo-3.1-4B 4.8B F16 10.2 GiB 262,144 ≤ 116 tok/s Fits
gemma-4-E2B 4.6B Q6_K 3.5 GiB 131,072 ≤ 514 tok/s Fits
gemma-4-E2B-it 4.6B BF16 6.1 GiB 131,072 ≤ 217 tok/s Fits
AgentCPM-Explore 4.4B Q6_K 5.7 GiB 111,360 ≤ 224 tok/s Fits
CapRL-Qwen3VL-4B 4.4B F16 10.4 GiB 79,616 ≤ 109 tok/s Fits
Holo2-4B 4.4B F16 10.4 GiB 79,616 ≤ 109 tok/s Fits
intent-aware-lfqa-qwen3-4b-baseline 4.4B F16 10.4 GiB 40,960 ≤ 109 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B F16 10.4 GiB 40,960 ≤ 109 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B F16 10.4 GiB 40,960 ≤ 109 tok/s Fits
intent-aware-lfqa-qwen3-4b-multiview 4.4B F16 10.4 GiB 40,960 ≤ 109 tok/s Fits
Spatial-SSRL-Qwen3VL-4B 4.4B F16 10.4 GiB 79,616 ≤ 109 tok/s Fits
ZwZ-4B 4.4B Q6_K 5.7 GiB 111,360 ≤ 224 tok/s Fits
Fara1.5-4B 4.2B BF16 10.2 GiB 262,144 ≤ 116 tok/s Fits
FrogNano-4B-2609 4.2B BF16 10.2 GiB 262,144 ≤ 116 tok/s Fits
Qwen3.5-4B 4.2B BF16 10.2 GiB 262,144 ≤ 116 tok/s Fits
Qwen3.5-4B-Base 4.2B F16 10.2 GiB 262,144 ≤ 116 tok/s Fits
UserRepGen-4B 4.2B BF16 10.2 GiB 262,144 ≤ 116 tok/s Fits
Riva-Translate-4B-Instruct-v1.1 4.2B Q6_K 6.0 GiB 8,192 ≤ 210 tok/s Fits
GELab-Zero-4B-preview 4.0B BF16 10.4 GiB 79,616 ≤ 109 tok/s Fits
Qwen3-4B 4.0B Q8_0 6.7 GiB 40,960 ≤ 184 tok/s Fits
Qwen3-4B-Instruct-2507 4.0B F16 10.4 GiB 79,616 ≤ 109 tok/s Fits
Qwen3-VL-4B-Instruct 4.0B BF16 10.4 GiB 79,616 ≤ 109 tok/s Fits
Qwen3-VL-4B-Thinking 4.0B BF16 10.4 GiB 79,616 ≤ 109 tok/s Fits
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B BF16 8.7 GiB 262,144 ≤ 139 tok/s Fits
gemma-3-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 125 tok/s Fits
medgemma-1.5-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 125 tok/s Fits
Nemotron-3-Content-Safety 3.9B Q6_K 5.4 GiB 131,072 ≤ 290 tok/s Fits
translategemma-4b-it 3.9B F16 9.9 GiB 131,072 ≤ 125 tok/s Fits
Phi-4-mini-instruct 3.8B BF16 10.0 GiB 91,392 ≤ 115 tok/s Fits
Apertus-v1.1-4B 3.8B Q6_K 4.4 GiB 4,096 ≤ 314 tok/s Fits
Phi-3.5-mini-instruct 3.8B Q8_0 8.3 GiB 40,448 ≤ 140 tok/s Fits
granite-4.2-3b 3.7B BF16 8.6 GiB 131,072 ≤ 135 tok/s Fits
BitCPM-CANN-3B-unquantized 3.6B Q6_K 4.3 GiB 32,768 ≤ 328 tok/s Fits
kanana-2-3b-instruct 3.5B F16 8.6 GiB 32,768 ≤ 136 tok/s Fits
Ministral-3-3B-Instruct-2512 3.4B BF16 8.9 GiB 121,088 ≤ 130 tok/s Fits
Ministral-3-3B-Reasoning-2512 3.4B BF16 8.9 GiB 121,088 ≤ 130 tok/s Fits
granite-vision-4.1-4b 3.4B BF16 8.6 GiB 131,072 ≤ 135 tok/s Fits
granite-4.1-3b 3.4B BF16 8.6 GiB 131,072 ≤ 135 tok/s Fits
granite-guardian-4.0-3b-toxicity-ja 3.4B Q6_K 4.7 GiB 131,072 ≤ 291 tok/s Fits
Qwen2.5-3B-Instruct 3.4B Q8_0 4.8 GiB 32,768 ≤ 281 tok/s Fits
tiny-aya-earth 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 142 tok/s Fits
tiny-aya-fire 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 142 tok/s Fits
tiny-aya-global 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 142 tok/s Fits
tiny-aya-water 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 142 tok/s Fits
Llama-3.2-3B-Instruct 3.2B BF16 8.5 GiB 116,224 ≤ 137 tok/s Fits
AI21-Jamba-Reasoning-3B 3.2B BF16 7.3 GiB 262,144 ≤ 166 tok/s Fits
AI21-Jamba2-3B 3.2B BF16 7.3 GiB 262,144 ≤ 166 tok/s Fits
kanana-2-3b-base 3.2B Q6_K 4.9 GiB 32,768 ≤ 274 tok/s Fits
SmolLM3-3B 3.1B BF16 7.9 GiB 65,536 ≤ 149 tok/s Fits
SmolLM3-3B-GSM8K-SFT 3.1B Q6_K 4.3 GiB 65,536 ≤ 322 tok/s Fits
LFM2-2.6B-Exp 2.7B F16 6.5 GiB 128,000 ≤ 191 tok/s Fits
d1-3B 2.7B BF16 6.7 GiB 32,768 ≤ 182 tok/s Fits
LFM2.5-2.6B 2.7B BF16 6.7 GiB 131,072 ≤ 182 tok/s Fits
LFM2.5-2.6B-Base 2.7B Q6_K 3.6 GiB 128,000 ≤ 429 tok/s Fits
LFM2.5-VL-3B 2.7B BF16 6.7 GiB 32,768 ≤ 182 tok/s Fits
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) Q6_K 3.6 GiB 32,768 ≤ 1,640 tok/s Fits
LFM2-2.6B-Longevity 2.6B F16 6.5 GiB 128,000 ≤ 191 tok/s Fits
LFM2-2.6B-Transcript 2.6B BF16 6.5 GiB 128,000 ≤ 191 tok/s Fits
LFM2-VL-3B 2.6B BF16 6.5 GiB 128,000 ≤ 191 tok/s Fits
MiniCPM5-2B 2.5B BF16 6.0 GiB 131,072 ≤ 208 tok/s Fits
MiniCPM5-2B-Base 2.5B Q6_K 3.4 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 459 tok/s Fits
CapRL-Qwen3VL-2B 2.0B F16 5.6 GiB 141,312 ≤ 230 tok/s Fits
HiPO-1.7B 2.0B Q6_K 3.6 GiB 40,960 ≤ 429 tok/s Fits
UI-Venus-1.5-2B 2.0B F16 5.6 GiB 141,312 ≤ 230 tok/s Fits
ZwZ-2B 2.0B F16 5.6 GiB 141,312 ≤ 230 tok/s Fits
Youtu-LLM-2B 2.0B Q6_K 3.2 GiB 131,072 ≤ 525 tok/s Fits
Youtu-LLM-2B-Base 2.0B Q6_K 3.2 GiB 131,072 ≤ 525 tok/s Fits
Qwen3.5-2B 1.9B BF16 5.4 GiB 262,144 ≤ 261 tok/s Fits
Qwen3.5-2B-Base 1.9B Q6_K 3.2 GiB 262,144 ≤ 612 tok/s Fits
Qwen3-1.7B 1.7B BF16 5.6 GiB 40,960 ≤ 230 tok/s Fits
Qwen3-VL-2B-Instruct 1.7B BF16 5.6 GiB 141,312 ≤ 230 tok/s Fits
Qwen3-VL-2B-Thinking 1.7B BF16 5.6 GiB 141,312 ≤ 230 tok/s Fits
SingGuard-2b 1.7B F16 5.6 GiB 141,312 ≤ 230 tok/s Fits
granite-4.0-1b 1.6B BF16 5.1 GiB 131,072 ≤ 256 tok/s Fits
Apertus-v1.1-1.5B 1.5B F16 3.8 GiB 4,096 ≤ 385 tok/s Fits
Apertus-v1.1-1.5B-Instruct 1.5B F16 3.8 GiB 4,096 ≤ 385 tok/s Fits
granite-4.0-h-1b 1.5B BF16 4.4 GiB 131,072 ≤ 337 tok/s Fits
Llama-3.2-1B-Instruct 1.2B BF16 4.0 GiB 131,072 ≤ 368 tok/s Fits
LFM2.5-1.2B-Base 1.2B BF16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-1.2B-Instruct 1.2B BF16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-1.2B-JP 1.2B F16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-1.2B-JP-202606 1.2B F16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-1.2B-Thinking 1.2B BF16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-VL-1.6B 1.2B BF16 3.7 GiB 128,000 ≤ 413 tok/s Fits
LFM2.5-VL-1.6B-Extract 1.2B F16 3.7 GiB 128,000 ≤ 413 tok/s Fits
MiniCPM5-1B 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,091 tok/s Fits
MiniCPM5-1B-Base 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,091 tok/s Fits
MiniCPM5-1B-SFT 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,091 tok/s Fits
Holo-3.1-0.8B 1.0B Q6_K 2.3 GiB 262,144 ≤ 1,401 tok/s Fits
MiniCPM-V-4.7-1B 1.0B F16 3.2 GiB 262,144 ≤ 628 tok/s Fits
gemma-3-1b-it 1.0B BF16 3.6 GiB 32,768 ≤ 493 tok/s Fits
Qwen3.5-0.8B 752M BF16 3.2 GiB 262,144 ≤ 627 tok/s Fits
Qwen3.5-0.8B-Base 752M Q6_K 2.3 GiB 262,144 ≤ 1,401 tok/s Fits
MiniCPM-V-4.6 752M F16 3.2 GiB 262,144 ≤ 628 tok/s Fits
MiniCPM-V-4.6-Thinking 752M F16 3.2 GiB 262,144 ≤ 628 tok/s Fits
Qwen3-0.6B 752M BF16 3.4 GiB 40,960 ≤ 473 tok/s Fits
HunyuanOCR 539M F16 3.1 GiB 32,768 ≤ 535 tok/s Fits
LFM2.5-350M 354M BF16 2.1 GiB 128,000 ≤ 1,245 tok/s Fits
LFM2.5-Encoder-350M-Diffusion 354M Q6_K 1.7 GiB 128,000 ≤ 2,574 tok/s Fits
LFM2.5-VL-450M 354M BF16 2.1 GiB 128,000 ≤ 1,245 tok/s Fits
LFM2.5-VL-450M-Extract 354M F16 2.1 GiB 128,000 ≤ 1,245 tok/s Fits
granite-4.0-350m 352M BF16 2.2 GiB 32,768 ≤ 1,073 tok/s Fits
granite-4.0-h-350m 340M BF16 2.1 GiB 32,768 ≤ 1,410 tok/s Fits
functiongemma-270m-it 268M BF16 2.1 GiB 32,768 ≤ 1,770 tok/s Fits
LFM2.5-230M 230M BF16 1.8 GiB 128,000 ≤ 1,799 tok/s Fits

Borderline models

Within the estimate error range: it may fit or it may not. Try a shorter context or a lower quantization.

Context 8,192 tokens. No quantization of these models fits; the one shown is the highest that is borderline.
Model Parameters Highest borderline quantization Available memory needed for “Fits” Result
Qwen3-Coder-Next-Base 79.7B (3.6B active) IQ2_M 27.2 GiB Tight
KAT-Dev-72B-Exp 72.7B IQ2_XXS 28.5 GiB Tight
Llama-3.1-70B-Instruct 70.6B IQ2_M 27.1 GiB Tight
QwQ-32B 32.8B Q5_K_M 25.7 GiB Tight
Qwen3-32B 32.8B Q5_K_M 25.7 GiB Tight
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 31.6B (3.2B active) Q4_K_M 23.3 GiB Tight

Models that don’t fit on one NVIDIA GeForce RTX 3090 Ti

Context 8,192 tokens. Even the lowest quantization does not fit on one card; the requirement shown is for that quantization.
Model Parameters Smallest quantization Available memory needed for “Fits” Several identical cards Result
Solar-Open-100B 103B (11.2B active) IQ2_XXS 29.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
DeepSeek-R1-Distill-Llama-70B 70.6B Q2_K 29.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Llama-3.3-70B-Instruct 70.6B Q2_K 29.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-Next-80B-A3B-Instruct 79.7B (3.6B active) Q2_K 30.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen2.5-72B-Instruct 73.0B Q2_K 30.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-Coder-Next 79.7B (3.6B active) Q2_K 30.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
GLM-4.5-Air-REAP-82B-A12B 81.9B (12.8B active) IQ2_XXS 31.1 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Step-3.5-Flash-REAP-121B-A11B 121B (11.4B active) IQ2_XXS 32.9 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Mistral-Small-4-119B-2603 119B (6.1B active) IQ2_XXS 34.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3.5-122B-A10B 122B (9.0B active) IQ2_XXS 35.0 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen-AgentWorld-35B-A3B 34.7B (2.9B active) Q8_0 37.6 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
MiniMax-M2.5-REAP-139B-A10B 139B (10.4B active) IQ2_XXS 39.2 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
INTELLECT-3 107B (12.8B active) IQ2_XXS 39.6 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Step-3.5-Flash-REAP-149B-A11B 149B (11.4B active) IQ2_XXS 40.1 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Llama-4-Scout-17B-16E-Instruct 108B (16.1B active) Q2_K 41.5 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.5-Air 107B (12.8B active) Q2_K 45.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.6V 107B (12.8B active) Q2_K 45.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.5-Flash 197B (11.5B active) IQ2_XXS 48.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Devstral-2-123B-Instruct-2512 125B Q2_K 49.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Mistral-Medium-3.5-128B 125B Q2_K 49.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 121B (12.2B active) IQ2_XXS 49.8 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-BF16 121B (12.2B active) IQ2_XXS 51.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gpt-oss-120b 117B (5.1B active) Q2_K 62.8 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.7 229B (10.4B active) IQ2_XXS 62.9 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Baichuan-M3-235B 235B (21.6B active) IQ2_XXS 63.2 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holo2-235B-A22B 235B (21.6B active) IQ2_XXS 63.2 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Nemotron-235B-A22B-GenRM 235B (21.6B active) IQ2_XXS 63.2 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
command-a-plus-05-2026-bf16 218B (25.0B active) IQ2_XXS 63.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 121B (12.2B active) Q4_0 71.8 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.7-REAP-268B-A32B 269B (32.8B active) IQ2_XXS 73.0 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.7-Flash 197B (11.5B active) IQ3_XXS 76.1 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Hy3 295B (20.2B active) IQ2_XXS 82.2 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiMo-V2.5 309B (14.8B active) IQ2_XXS 82.4 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.7-REAP-218B-A32B 218B (32.8B active) Q2_K 82.9 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2 229B (10.4B active) Q2_K 84.9 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.1 229B (10.4B active) Q2_K 84.9 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.5 229B (10.4B active) Q2_K 84.9 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-235B-A22B-Instruct-2507 235B (21.6B active) Q2_K 86.7 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-VL-235B-A22B-Instruct 235B (21.6B active) Q2_K 86.7 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-5.3-Flash-BF16 313B (16.7B active) IQ2_XXS 92.0 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Laguna-S-2.1 118B (8.1B active) Q4_K_M 95.9 GiB Borderline with 8 cards. Doesn't fit
Trinity-Large-Base 399B (12.8B active) IQ2_XXS 96.4 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Trinity-Large-TrueBase 399B (12.8B active) IQ2_XXS 96.4 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.6-REAP-268B-A32B 269B (32.8B active) Q2_K 100.9 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Trinity-Large-Thinking 399B (12.8B active) IQ2_XXS 107.1 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiMo-V2-Flash 309B (14.8B active) Q2_K 111.6 GiB 6 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Intern-S2-397B 396B (16.3B active) IQ2_XXS 114.3 GiB 7 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiMo-V2.6-Flash-MOPD 309B (14.8B active) Q2_K 124.9 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiMo-V2.6-Flash-RL 309B (14.8B active) Q2_K 124.9 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
K-EXAONE-236B-A23B 237B (22.7B active) IQ4_XS 126.3 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.5 353B (32.9B active) Q2_K 130.7 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.7 353B (32.9B active) Q2_K 130.7 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-REAP-363B-A35B 363B (34.5B active) Q2_K 132.7 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-235B-A22B 235B (21.6B active) Q4_K_M 141.9 GiB 8 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-480B-A35B-Instruct 480B (34.5B active) Q2_K 174.3 GiB Borderline with 8 cards. Doesn't fit
Qwen3.5-397B-A17B 396B (16.3B active) Q3_K_M 175.6 GiB Borderline with 8 cards. Doesn't fit
GLM-5.1 744B (40.8B active) IQ2_XXS 197.6 GiB Borderline with 8 cards. Doesn't fit
DeepSeek-V3.2 671B (36.6B active) Q2_K 242.1 GiB Does not fit even on 8 cards. Doesn't fit
cogito-671b-v2.1 671B (36.6B active) Q2_K 242.4 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-V3.1 671B (36.6B active) Q2_K 242.4 GiB Does not fit even on 8 cards. Doesn't fit
Mistral-Large-3-675B-Instruct-2512 673B (39.0B active) Q2_K 243.8 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-V3 671B (36.6B active) Q2_K 257.8 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2.6 1.03T (31.7B active) IQ2_XXS 267.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5 744B (40.8B active) Q2_K 268.9 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.5-Pro 1.02T (41.0B active) IQ2_XXS 270.4 GiB Does not fit even on 8 cards. Doesn't fit
DeepSeek-R1 671B (36.6B active) Q2_K 280.3 GiB Does not fit even on 8 cards. Doesn't fit
Muse-Spark-Open-816B-A42B 820B (44.4B active) Q2_K 301.0 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.3-Flash 313B (16.7B active) Q8_0 327.9 GiB Does not fit even on 8 cards. Doesn't fit
Ling-1T 1.00T (49.8B active) Q2_K 360.6 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2-Instruct 1.03T (31.7B active) Q2_K 367.4 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2.5 1.03T (31.7B active) Q2_K 368.0 GiB Does not fit even on 8 cards. Doesn't fit
Kimi-K2-Thinking 1.03T (31.7B active) Q2_K 368.3 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Pro-MOPD 1.02T (41.0B active) Q2_K 411.6 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Pro-RL 1.02T (41.0B active) Q2_K 411.6 GiB Does not fit even on 8 cards. Doesn't fit
Beam-1.0-501B-A23B 501B (22.7B active) Q8_0 523.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.2 744B (40.8B active) Q8_0 776.4 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.3 744B (40.8B active) Q8_0 776.4 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3.8-2.4T-A95B 2.42T (93.3B active) Q8_0 2,524.1 GiB Does not fit even on 8 cards. Doesn't fit

The speed ceiling is memory bandwidth divided by the bytes read per generated token. It is a theoretical upper bound; public llama.cpp benchmarks typically reach about half to four-fifths of it, and small models and mixture-of-experts models often less. Public benchmarks

Other devices with 24 GB