DeskGPU
English

NVIDIA GeForce RTX 4080: 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 4080 has 16 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)
16 GB
Memory type
GDDR6X
Memory bus width
256 bit
Memory bandwidth
717 GB/s
Board power (TDP)
320 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): 12.88 GiB per card = 16 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 16 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
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) IQ2_M 12.8 GiB 14,848 ≤ 539 tok/s Fits
Holo4-35B-A3B 34.7B (2.9B active) IQ2_XXS 12.0 GiB 48,640 ≤ 418 tok/s Fits
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.1 GiB 89,600 ≤ 517 tok/s Fits
KAT-Coder-V2.5-Dev 34.7B (2.9B active) IQ2_XXS 11.3 GiB 77,056 ≤ 435 tok/s Fits
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) IQ2_XXS 10.9 GiB 96,512 ≤ 581 tok/s Fits
Qwen3.6-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.3 GiB 77,056 ≤ 435 tok/s Fits
Laguna-XS-2.1 33.4B (2.8B active) IQ2_XXS 11.1 GiB 50,944 ≤ 393 tok/s Fits
Cosmos-Reason2-32B 32.8B IQ2_XXS 12.0 GiB 11,264 ≤ 65.7 tok/s Fits
FrogBoss-32B-2510 32.8B IQ2_XXS 12.0 GiB 11,264 ≤ 65.7 tok/s Fits
Nemotron-Terminal-32B 32.8B IQ2_XXS 12.0 GiB 11,264 ≤ 65.7 tok/s Fits
SERA-32B 32.8B IQ2_XXS 12.0 GiB 11,264 ≤ 65.7 tok/s Fits
WebWorld-32B 32.8B IQ2_XXS 12.0 GiB 11,264 ≤ 65.7 tok/s Fits
Olmo-3.1-32B-Instruct-DPO 32.2B IQ2_XXS 11.8 GiB 12,032 ≤ 72.2 tok/s Fits
Olmo-3-1125-32B 32.2B IQ2_XXS 11.8 GiB 12,032 ≤ 72.2 tok/s Fits
Olmo-3-32B-Think-DPO 32.2B IQ2_XXS 11.8 GiB 12,032 ≤ 72.2 tok/s Fits
Olmo-3-32B-Think-SFT 32.2B IQ2_XXS 11.8 GiB 12,032 ≤ 72.2 tok/s Fits
North-Mini-Code-1.0 30.5B (3.3B active) IQ2_M 12.7 GiB 9,728 ≤ 337 tok/s Fits
GLM-4.7-Flash 29.9B (3.6B active) Q2_K 12.8 GiB 9,984 ≤ 319 tok/s Fits
Muse-Glimmer-30B 27.9B IQ3_XXS 12.6 GiB 24,576 ≤ 64.3 tok/s Fits
Fara1.5-27B 26.9B IQ2_M 12.5 GiB 13,312 ≤ 67.6 tok/s Fits
Holo4-27B 26.9B Q2_K 12.7 GiB 10,240 ≤ 66.3 tok/s Fits
Qwen3.8-27B 26.9B Q2_K 12.5 GiB 14,080 ≤ 67.9 tok/s Fits
Qwen3.8-3.6-27B-blend 26.9B Q2_K 12.5 GiB 14,080 ≤ 67.9 tok/s Fits
UI-Mate-27B 26.9B IQ2_M 12.5 GiB 13,312 ≤ 67.6 tok/s Fits
UI-Mate-democua-27B 26.9B Q2_K 12.7 GiB 10,240 ≤ 66.3 tok/s Fits
Trinity-Mini 26.1B (3.1B active) IQ3_XXS 12.1 GiB 48,640 ≤ 408 tok/s Fits
Trinity-Mini-Base 26.1B (3.1B active) IQ3_XXS 11.8 GiB 68,096 ≤ 459 tok/s Fits
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) IQ3_XXS 11.5 GiB 4,096 ≤ 480 tok/s Fits
gemma-4-26B-A4B-it 25.2B (3.8B active) IQ2_XXS 12.1 GiB 43,520 ≤ 313 tok/s Fits
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) IQ3_XXS 11.8 GiB 19,200 ≤ 318 tok/s Fits
Devstral-Small-2-24B-Instruct-2512 23.6B Q2_K 11.1 GiB 18,944 ≤ 71.7 tok/s Fits
Mistral-Small-3.2-24B-Instruct-2506 23.6B Q2_K 11.1 GiB 18,944 ≤ 71.7 tok/s Fits
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q3_K_M 12.7 GiB 11,776 ≤ 287 tok/s Fits
EuroLLM-22B-2512 22.6B IQ3_XXS 11.5 GiB 14,336 ≤ 68.8 tok/s Fits
EuroLLM-22B-Instruct-2512 22.6B IQ3_XXS 11.5 GiB 14,336 ≤ 68.8 tok/s Fits
gpt-oss-20b 20.9B (3.6B active) Q6_K 12.8 GiB 9,728 ≤ 265 tok/s Fits
DeepSeek-R1-Distill-Qwen-14B 14.8B Q5_K_M 12.7 GiB 9,216 ≤ 61.9 tok/s Fits
Qwen2.5-14B-Instruct 14.8B Q5_K_M 12.7 GiB 9,216 ≤ 61.9 tok/s Fits
ContextPilot-14B 14.8B Q5_K_M 12.6 GiB 9,472 ≤ 62.1 tok/s Fits
FrogMini-14B-2510 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
JanusCoder-14B 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
Nemotron-Cascade-14B-Thinking 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
Nemotron-Terminal-14B 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
NousCoder-14B 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
Qwen3-14B 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
Qwen3-Nemotron-14B-BRRM 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
WebWorld-14B 14.8B Q5_K_M 12.4 GiB 11,008 ≤ 63.4 tok/s Fits
phi-4 14.7B Q5_K_M 12.8 GiB 8,448 ≤ 61.1 tok/s Fits
Apriel-1.6-15b-Thinker 14.4B Q5_K_M 12.5 GiB 10,240 ≤ 62.8 tok/s Fits
Ministral-3-14B-Instruct-2512 13.5B Q5_K_M 11.6 GiB 16,128 ≤ 68.3 tok/s Fits
Ministral-3-14B-Reasoning-2512 13.5B Q5_K_M 11.6 GiB 16,128 ≤ 68.3 tok/s Fits
Mistral-Nemo-Instruct-2407 12.2B Q6_K 11.9 GiB 14,080 ≤ 66.1 tok/s Fits
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q6_K 12.1 GiB 57,600 ≤ 341 tok/s Fits
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) Q6_K 12.1 GiB 57,600 ≤ 341 tok/s Fits
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) Q6_K 12.2 GiB 50,688 ≤ 324 tok/s Fits
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 57,600 ≤ 341 tok/s Fits
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) Q6_K 12.2 GiB 50,688 ≤ 324 tok/s Fits
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 57,600 ≤ 341 tok/s Fits
gemma-4-12B-it 11.9B Q6_K 12.7 GiB 15,360 ≤ 70.0 tok/s Fits
gemma-3-12b-it 11.8B Q5_K_M 11.8 GiB 23,808 ≤ 77.0 tok/s Fits
translategemma-12b-it 11.8B Q5_K_M 11.8 GiB 23,808 ≤ 77.0 tok/s Fits
Bielik-11B-v3.0-Instruct 11.2B Q6_K 11.8 GiB 13,312 ≤ 66.8 tok/s Fits
AutoGLM-Phone-9B 9.4B Q8_0 10.8 GiB 57,344 ≤ 74.2 tok/s Fits
AutoGLM-Phone-9B-Multilingual 9.4B Q6_K 9.2 GiB 65,536 ≤ 88.7 tok/s Fits
GLM-4.6V-Flash 9.4B Q8_0 10.8 GiB 57,344 ≤ 74.2 tok/s Fits
gemma-2-9b-it 9.2B Q6_K 12.0 GiB 8,192 ≤ 72.3 tok/s Fits
EuroLLM-9B-Instruct-2512 9.2B Q8_0 11.6 GiB 15,360 ≤ 67.8 tok/s Fits
Fara1.5-9B 9.0B Q8_0 10.3 GiB 84,224 ≤ 82.2 tok/s Fits
Holo-3.1-9B 9.0B Q8_0 10.3 GiB 84,736 ≤ 82.4 tok/s Fits
MiMo-V2.6-Distill-Qwen-9B 9.0B Q8_0 10.3 GiB 84,224 ≤ 82.2 tok/s Fits
Qwen3.5-9B 9.0B Q8_0 10.3 GiB 84,736 ≤ 82.4 tok/s Fits
Qwen3.5-9B-Base 9.0B Q8_0 10.3 GiB 84,736 ≤ 82.4 tok/s Fits
UI-Mate-9B 9.0B Q8_0 10.3 GiB 84,224 ≤ 82.2 tok/s Fits
UI-Venus-2-9B 9.0B Q8_0 10.3 GiB 84,224 ≤ 82.2 tok/s Fits
NVIDIA-Nemotron-Nano-9B-v2 8.9B Q8_0 10.6 GiB 131,072 ≤ 80.0 tok/s Fits
granite-4.1-8b 8.8B Q8_0 11.3 GiB 17,664 ≤ 70.0 tok/s Fits
granite-4.2-8b 8.8B Q8_0 11.3 GiB 17,664 ≤ 70.0 tok/s Fits
Ministral-3-8B-Instruct-2512 8.5B Q8_0 10.7 GiB 23,808 ≤ 74.8 tok/s Fits
Ministral-3-8B-Reasoning-2512 8.5B Q8_0 10.7 GiB 23,808 ≤ 74.8 tok/s Fits
LFM2.5-8B-A1B 8.5B (1.7B active) Q8_0 10.2 GiB 128,000 ≤ 378 tok/s Fits
granite-guardian-4.1-8b 8.4B Q8_0 11.3 GiB 17,664 ≤ 70.0 tok/s Fits
LFM2-8B-A1B 8.3B (1.6B active) Q8_0 10.1 GiB 128,000 ≤ 407 tok/s Fits
rnj-1-instruct 8.3B Q8_0 11.0 GiB 22,528 ≤ 72.4 tok/s Fits
AesCode-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
ArmorOCR 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
AstaBrief_8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
ContextPilot-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
Cosmos-Reason2-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
DeepSeek-R1-0528-Qwen3-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Holo2-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
intent-aware-lfqa-qwen3-8b-baseline 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-8b-multiview 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
JanusCoder-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
MathForm-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Nemotron-Cascade-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Nemotron-Cascade-8B-Thinking 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Nemotron-Orchestrator-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Nemotron-Terminal-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
Qwen3-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Qwen3-Nemotron-8B-BRRM 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
Qwen3-VL-8B-Instruct 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Qwen3-VL-8B-Thinking 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
RLVR-8B-0926 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
Step3-VL-10B-Base 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
UI-Venus-1.5-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
WebWorld-8B 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
ZwZ-8B 8.2B Q6_K 8.6 GiB 37,376 ≤ 96.7 tok/s Fits
MiniCPM-o-4_5 8.2B Q8_0 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
granite-3.3-8b-instruct 8.2B Q8_0 11.1 GiB 18,944 ≤ 71.5 tok/s Fits
granite-guardian-3.2-8b-factuality-detection 8.2B Q8_0 11.1 GiB 18,944 ≤ 71.5 tok/s Fits
intent-aware-lfqa-llama3-8b-baseline 8.0B Q8_0 10.2 GiB 28,928 ≤ 79.2 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B Q8_0 10.2 GiB 28,928 ≤ 79.2 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B Q8_0 10.2 GiB 28,928 ≤ 79.2 tok/s Fits
intent-aware-lfqa-llama3-8b-multiview 8.0B Q8_0 10.2 GiB 28,928 ≤ 79.2 tok/s Fits
DeepSeek-R1-Distill-Llama-8B 8.0B Q8_0 10.2 GiB 28,928 ≤ 79.2 tok/s Fits
HARC-Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 42,496 ≤ 99.2 tok/s Fits
Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 42,496 ≤ 99.2 tok/s Fits
AprielGuard 7.9B Q6_K 7.9 GiB 58,880 ≤ 107 tok/s Fits
MiMo-Embodied-7B 7.6B Q6_K 8.1 GiB 40,448 ≤ 103 tok/s Fits
DeepSeek-R1-Distill-Qwen-7B 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
Fara-7B 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
HARC-Qwen2.5-7B-Instruct 7.6B Q6_K 7.5 GiB 32,768 ≤ 114 tok/s Fits
JanusCoderV-7B 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
olmOCR-2-7B-1025 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
Qwen2.5-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 89.8 tok/s Fits
Qwen2.5-Coder-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 89.8 tok/s Fits
Qwen2.5-VL-7B-Instruct 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
Qwen2.5-VL-7B-Surg-CholecT50 7.6B Q8_0 9.1 GiB 72,192 ≤ 89.8 tok/s Fits
Spatial-SSRL-7B 7.6B Q6_K 7.5 GiB 100,864 ≤ 114 tok/s Fits
X-Reasoner-7B 7.6B Q6_K 7.5 GiB 100,864 ≤ 114 tok/s Fits
ZwZ-7B 7.6B Q6_K 7.5 GiB 100,864 ≤ 114 tok/s Fits
gemma-4-E4B 7.5B F16 11.0 GiB 111,872 ≤ 75.0 tok/s Fits
gemma-4-E4B-it 7.5B BF16 11.0 GiB 111,872 ≤ 75.0 tok/s Fits
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q8_0 10.2 GiB 24,320 ≤ 78.4 tok/s Fits
ContextPilot-E4B 7.5B F16 10.9 GiB 118,016 ≤ 75.9 tok/s Fits
Olmo-3.1-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3.1-7B-RL-Zero-Math 7.3B Q8_0 12.7 GiB 8,448 ≤ 71.7 tok/s Fits
Olmo-3-7B-Instruct 7.3B Q8_0 12.7 GiB 8,448 ≤ 71.7 tok/s Fits
Olmo-3-7B-Instruct-DPO 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-Instruct-SFT 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-RL-Zero-General 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-RL-Zero-IF 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-RL-Zero-Math 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-RL-Zero-Mix 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-Think 7.3B Q8_0 12.7 GiB 8,448 ≤ 71.7 tok/s Fits
Olmo-3-7B-Think-DPO 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Olmo-3-7B-Think-SFT 7.3B Q6_K 11.0 GiB 11,520 ≤ 86.0 tok/s Fits
Mistral-7B-Instruct-v0.2 7.2B Q6_K 8.1 GiB 32,768 ≤ 104 tok/s Fits
Trinity-Nano-Base 6.1B (819M active) Q6_K 6.7 GiB 131,072 ≤ 796 tok/s Fits
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) Q6_K 6.4 GiB 4,096 ≤ 852 tok/s Fits
Trinity-Nano-Preview 6.1B (819M active) Q8_0 8.1 GiB 131,072 ≤ 654 tok/s Fits
Youtu-VL-4B-Instruct 4.9B Q6_K 5.9 GiB 32,768 ≤ 162 tok/s Fits
Holo-3.1-4B 4.8B F16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
gemma-4-E2B 4.6B Q6_K 3.5 GiB 131,072 ≤ 366 tok/s Fits
gemma-4-E2B-it 4.6B BF16 6.1 GiB 131,072 ≤ 154 tok/s Fits
AgentCPM-Explore 4.4B Q6_K 5.7 GiB 56,832 ≤ 159 tok/s Fits
CapRL-Qwen3VL-4B 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Holo2-4B 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-4b-baseline 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
intent-aware-lfqa-qwen3-4b-multiview 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Spatial-SSRL-Qwen3VL-4B 4.4B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
ZwZ-4B 4.4B Q6_K 5.7 GiB 56,832 ≤ 159 tok/s Fits
Fara1.5-4B 4.2B BF16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
FrogNano-4B-2609 4.2B BF16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
Qwen3.5-4B 4.2B BF16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
Qwen3.5-4B-Base 4.2B F16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
UserRepGen-4B 4.2B BF16 10.2 GiB 85,504 ≤ 82.6 tok/s Fits
Riva-Translate-4B-Instruct-v1.1 4.2B Q6_K 6.0 GiB 8,192 ≤ 150 tok/s Fits
GELab-Zero-4B-preview 4.0B BF16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Qwen3-4B 4.0B Q8_0 6.7 GiB 40,960 ≤ 131 tok/s Fits
Qwen3-4B-Instruct-2507 4.0B F16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Qwen3-VL-4B-Instruct 4.0B BF16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
Qwen3-VL-4B-Thinking 4.0B BF16 10.4 GiB 25,088 ≤ 77.5 tok/s Fits
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B BF16 8.7 GiB 237,312 ≤ 98.7 tok/s Fits
gemma-3-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 89.1 tok/s Fits
medgemma-1.5-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 89.1 tok/s Fits
Nemotron-3-Content-Safety 3.9B Q6_K 5.4 GiB 131,072 ≤ 206 tok/s Fits
translategemma-4b-it 3.9B F16 9.9 GiB 131,072 ≤ 89.1 tok/s Fits
Phi-4-mini-instruct 3.8B BF16 10.0 GiB 30,208 ≤ 82.0 tok/s Fits
Apertus-v1.1-4B 3.8B Q6_K 4.4 GiB 4,096 ≤ 223 tok/s Fits
Phi-3.5-mini-instruct 3.8B Q8_0 8.3 GiB 19,712 ≤ 99.9 tok/s Fits
granite-4.2-3b 3.7B BF16 8.6 GiB 59,904 ≤ 95.9 tok/s Fits
BitCPM-CANN-3B-unquantized 3.6B Q6_K 4.3 GiB 32,768 ≤ 233 tok/s Fits
kanana-2-3b-instruct 3.5B F16 8.6 GiB 32,768 ≤ 96.4 tok/s Fits
Ministral-3-3B-Instruct-2512 3.4B BF16 8.9 GiB 45,824 ≤ 92.7 tok/s Fits
Ministral-3-3B-Reasoning-2512 3.4B BF16 8.9 GiB 45,824 ≤ 92.7 tok/s Fits
granite-vision-4.1-4b 3.4B BF16 8.6 GiB 59,904 ≤ 95.9 tok/s Fits
granite-4.1-3b 3.4B BF16 8.6 GiB 59,904 ≤ 95.9 tok/s Fits
granite-guardian-4.0-3b-toxicity-ja 3.4B Q6_K 4.7 GiB 107,776 ≤ 207 tok/s Fits
Qwen2.5-3B-Instruct 3.4B Q8_0 4.8 GiB 32,768 ≤ 200 tok/s Fits
tiny-aya-earth 3.3B BF16 8.7 GiB 190,720 ≤ 101 tok/s Fits
tiny-aya-fire 3.3B BF16 8.7 GiB 190,720 ≤ 101 tok/s Fits
tiny-aya-global 3.3B BF16 8.7 GiB 190,720 ≤ 101 tok/s Fits
tiny-aya-water 3.3B BF16 8.7 GiB 190,720 ≤ 101 tok/s Fits
Llama-3.2-3B-Instruct 3.2B BF16 8.5 GiB 46,336 ≤ 97.3 tok/s Fits
AI21-Jamba-Reasoning-3B 3.2B BF16 7.3 GiB 262,144 ≤ 118 tok/s Fits
AI21-Jamba2-3B 3.2B BF16 7.3 GiB 262,144 ≤ 118 tok/s Fits
kanana-2-3b-base 3.2B Q6_K 4.9 GiB 32,768 ≤ 195 tok/s Fits
SmolLM3-3B 3.1B BF16 7.9 GiB 65,536 ≤ 106 tok/s Fits
SmolLM3-3B-GSM8K-SFT 3.1B Q6_K 4.3 GiB 65,536 ≤ 229 tok/s Fits
LFM2-2.6B-Exp 2.7B F16 6.5 GiB 128,000 ≤ 136 tok/s Fits
d1-3B 2.7B BF16 6.7 GiB 32,768 ≤ 130 tok/s Fits
LFM2.5-2.6B 2.7B BF16 6.7 GiB 131,072 ≤ 130 tok/s Fits
LFM2.5-2.6B-Base 2.7B Q6_K 3.6 GiB 128,000 ≤ 305 tok/s Fits
LFM2.5-VL-3B 2.7B BF16 6.7 GiB 32,768 ≤ 130 tok/s Fits
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) Q6_K 3.6 GiB 32,768 ≤ 1,166 tok/s Fits
LFM2-2.6B-Longevity 2.6B F16 6.5 GiB 128,000 ≤ 136 tok/s Fits
LFM2-2.6B-Transcript 2.6B BF16 6.5 GiB 128,000 ≤ 136 tok/s Fits
LFM2-VL-3B 2.6B BF16 6.5 GiB 128,000 ≤ 136 tok/s Fits
MiniCPM5-2B 2.5B BF16 6.0 GiB 131,072 ≤ 148 tok/s Fits
MiniCPM5-2B-Base 2.5B Q6_K 3.4 GiB 221,696 ≤ 326 tok/s Fits
CapRL-Qwen3VL-2B 2.0B F16 5.6 GiB 71,424 ≤ 164 tok/s Fits
HiPO-1.7B 2.0B Q6_K 3.6 GiB 40,960 ≤ 305 tok/s Fits
UI-Venus-1.5-2B 2.0B F16 5.6 GiB 71,424 ≤ 164 tok/s Fits
ZwZ-2B 2.0B F16 5.6 GiB 71,424 ≤ 164 tok/s Fits
Youtu-LLM-2B 2.0B Q6_K 3.2 GiB 131,072 ≤ 373 tok/s Fits
Youtu-LLM-2B-Base 2.0B Q6_K 3.2 GiB 131,072 ≤ 373 tok/s Fits
Qwen3.5-2B 1.9B BF16 5.4 GiB 262,144 ≤ 185 tok/s Fits
Qwen3.5-2B-Base 1.9B Q6_K 3.2 GiB 262,144 ≤ 436 tok/s Fits
Qwen3-1.7B 1.7B BF16 5.6 GiB 40,960 ≤ 164 tok/s Fits
Qwen3-VL-2B-Instruct 1.7B BF16 5.6 GiB 71,424 ≤ 164 tok/s Fits
Qwen3-VL-2B-Thinking 1.7B BF16 5.6 GiB 71,424 ≤ 164 tok/s Fits
SingGuard-2b 1.7B F16 5.6 GiB 71,424 ≤ 164 tok/s Fits
granite-4.0-1b 1.6B BF16 5.1 GiB 102,144 ≤ 182 tok/s Fits
Apertus-v1.1-1.5B 1.5B F16 3.8 GiB 4,096 ≤ 274 tok/s Fits
Apertus-v1.1-1.5B-Instruct 1.5B F16 3.8 GiB 4,096 ≤ 274 tok/s Fits
granite-4.0-h-1b 1.5B BF16 4.4 GiB 131,072 ≤ 240 tok/s Fits
Llama-3.2-1B-Instruct 1.2B BF16 4.0 GiB 131,072 ≤ 262 tok/s Fits
LFM2.5-1.2B-Base 1.2B BF16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-1.2B-Instruct 1.2B BF16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-1.2B-JP 1.2B F16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-1.2B-JP-202606 1.2B F16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-1.2B-Thinking 1.2B BF16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-VL-1.6B 1.2B BF16 3.7 GiB 128,000 ≤ 294 tok/s Fits
LFM2.5-VL-1.6B-Extract 1.2B F16 3.7 GiB 128,000 ≤ 294 tok/s Fits
MiniCPM5-1B 1.1B Q6_K 2.2 GiB 131,072 ≤ 776 tok/s Fits
MiniCPM5-1B-Base 1.1B Q6_K 2.2 GiB 131,072 ≤ 776 tok/s Fits
MiniCPM5-1B-SFT 1.1B Q6_K 2.2 GiB 131,072 ≤ 776 tok/s Fits
Holo-3.1-0.8B 1.0B Q6_K 2.3 GiB 262,144 ≤ 997 tok/s Fits
MiniCPM-V-4.7-1B 1.0B F16 3.2 GiB 262,144 ≤ 446 tok/s Fits
gemma-3-1b-it 1.0B BF16 3.6 GiB 32,768 ≤ 351 tok/s Fits
Qwen3.5-0.8B 752M BF16 3.2 GiB 262,144 ≤ 446 tok/s Fits
Qwen3.5-0.8B-Base 752M Q6_K 2.3 GiB 262,144 ≤ 997 tok/s Fits
MiniCPM-V-4.6 752M F16 3.2 GiB 262,144 ≤ 446 tok/s Fits
MiniCPM-V-4.6-Thinking 752M F16 3.2 GiB 262,144 ≤ 446 tok/s Fits
Qwen3-0.6B 752M BF16 3.4 GiB 40,960 ≤ 336 tok/s Fits
HunyuanOCR 539M F16 3.1 GiB 32,768 ≤ 381 tok/s Fits
LFM2.5-350M 354M BF16 2.1 GiB 128,000 ≤ 885 tok/s Fits
LFM2.5-Encoder-350M-Diffusion 354M Q6_K 1.7 GiB 128,000 ≤ 1,831 tok/s Fits
LFM2.5-VL-450M 354M BF16 2.1 GiB 128,000 ≤ 885 tok/s Fits
LFM2.5-VL-450M-Extract 354M F16 2.1 GiB 128,000 ≤ 885 tok/s Fits
granite-4.0-350m 352M BF16 2.2 GiB 32,768 ≤ 763 tok/s Fits
granite-4.0-h-350m 340M BF16 2.1 GiB 32,768 ≤ 1,003 tok/s Fits
functiongemma-270m-it 268M BF16 2.1 GiB 32,768 ≤ 1,259 tok/s Fits
LFM2.5-230M 230M BF16 1.8 GiB 128,000 ≤ 1,280 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
AI21-Jamba2-Mini 51.6B (11.8B active) Q2_K 19.0 GiB Tight
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) Q2_K 19.1 GiB Tight
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) Q2_K 18.6 GiB Tight
Hermes-4.3-36B 36.2B IQ3_XXS 16.9 GiB Tight
Holo-3.1-35B-A3B 34.7B (2.9B active) Q3_K_M 18.1 GiB Tight
Holo3-35B-A3B 34.7B (2.9B active) Q3_K_M 18.1 GiB Tight
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB Tight
DeepSeek-R1-Distill-Qwen-32B 32.8B Q3_K_M 18.7 GiB Tight
Qwen2.5-32B-Instruct 32.8B Q3_K_M 18.7 GiB Tight
Qwen2.5-Coder-32B-Instruct 32.8B Q3_K_M 18.7 GiB Tight
AesCode-32B 32.8B Q3_K_M 19.3 GiB Tight
Qwen3-VL-32B-Instruct 32.8B Q3_K_M 18.8 GiB Tight
Qwen3-VL-32B-Thinking 32.8B Q3_K_M 18.8 GiB Tight
Olmo-3.1-32B-Instruct 32.2B IQ4_XS 20.1 GiB Tight
Olmo-3.1-32B-Think 32.2B IQ4_XS 20.1 GiB Tight
Olmo-3-32B-Think 32.2B IQ4_XS 20.1 GiB Tight
Holotron4-30B-A3B 31.6B (3.2B active) Q4_0 19.0 GiB Tight
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) Q4_0 19.2 GiB Tight
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q4_0 19.0 GiB Tight
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.3 GiB Tight
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.2 GiB Tight
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.0 GiB Tight
gemma-4-31B 30.7B Q3_K_M 20.9 GiB Tight
gemma-4-31B-it 30.7B IQ4_XS 21.9 GiB Tight
Ising-Calibration-1.5-31B-BF16 30.7B Q3_K_M 21.5 GiB Tight
Holo2-30B-A3B 30.5B (3.0B active) IQ4_XS 18.2 GiB Tight
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q4_0 19.0 GiB Tight
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q4_0 19.0 GiB Tight
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q4_0 19.0 GiB Tight
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) IQ4_XS 18.2 GiB Tight
granite-4.2-30b 29.3B Q4_0 19.4 GiB Tight
granite-4.1-30b 28.9B Q4_0 19.4 GiB Tight
gemma-2-27b-it 27.2B IQ4_XS 19.1 GiB Tight
gemma-3-27b-it 27.0B Q4_K_M 20.3 GiB Tight
translategemma-27b-it 27.0B Q4_K_M 20.3 GiB Tight
Qwen3.5-27B 26.9B Q4_K_M 18.4 GiB Tight
Qwen3.6-27B 26.9B Q4_K_M 18.4 GiB Tight
gemma-4-26B-A4B 25.2B (3.8B active) Q4_K_M 19.1 GiB Tight
LFM2.5-24B-A2B 24.0B (2.5B active) Q5_K_M 18.1 GiB Tight
LFM2-24B-A2B 23.8B (2.3B active) Q5_K_M 18.0 GiB Tight
OptiMind-SFT 20.9B (3.6B active) Q5_K_M 17.8 GiB Tight
gemma-4-12B 11.9B Q8_0 15.6 GiB Tight

Models that don’t fit on one NVIDIA GeForce RTX 4080

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
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Llama-3.1-70B-Instruct 70.6B IQ2_XXS 22.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-Coder-Next-Base 79.7B (3.6B active) IQ2_XXS 22.3 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Qwen3-32B 32.8B Q4_K_M 22.4 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
QwQ-32B 32.8B Q4_K_M 22.5 GiB 2 identical cards (default even split) are expected to fit. Doesn't fit
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 31.6B (3.2B active) Q4_K_M 23.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
KAT-Dev-72B-Exp 72.7B IQ2_XXS 28.5 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Solar-Open-100B 103B (11.2B active) IQ2_XXS 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
DeepSeek-R1-Distill-Llama-70B 70.6B Q2_K 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Llama-3.3-70B-Instruct 70.6B Q2_K 29.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Next-80B-A3B-Instruct 79.7B (3.6B active) Q2_K 30.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen2.5-72B-Instruct 73.0B Q2_K 30.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-Next 79.7B (3.6B active) Q2_K 30.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
GLM-4.5-Air-REAP-82B-A12B 81.9B (12.8B active) IQ2_XXS 31.1 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.5-Flash-REAP-121B-A11B 121B (11.4B active) IQ2_XXS 32.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Mistral-Small-4-119B-2603 119B (6.1B active) IQ2_XXS 34.3 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3.5-122B-A10B 122B (9.0B active) IQ2_XXS 35.0 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen-AgentWorld-35B-A3B 34.7B (2.9B active) Q8_0 37.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniMax-M2.5-REAP-139B-A10B 139B (10.4B active) IQ2_XXS 39.2 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
INTELLECT-3 107B (12.8B active) IQ2_XXS 39.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Step-3.5-Flash-REAP-149B-A11B 149B (11.4B active) IQ2_XXS 40.1 GiB 4 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 4 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 5 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 5 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 5 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 5 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 5 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 5 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 5 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 7 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 6 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 6 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 6 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 6 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 7 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 7 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 7 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 8 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 8 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 Borderline with 8 cards. Doesn't fit
GLM-4.7-REAP-218B-A32B 218B (32.8B active) Q2_K 82.9 GiB 8 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 8 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 8 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 8 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 8 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 8 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 Borderline with 8 cards. 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 Borderline with 8 cards. Doesn't fit
Trinity-Large-TrueBase 399B (12.8B active) IQ2_XXS 96.4 GiB Borderline with 8 cards. Doesn't fit
GLM-4.6-REAP-268B-A32B 269B (32.8B active) Q2_K 100.9 GiB Borderline with 8 cards. Doesn't fit
Trinity-Large-Thinking 399B (12.8B active) IQ2_XXS 107.1 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2-Flash 309B (14.8B active) Q2_K 111.6 GiB Borderline with 8 cards. Doesn't fit
Intern-S2-397B 396B (16.3B active) IQ2_XXS 114.3 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2.6-Flash-MOPD 309B (14.8B active) Q2_K 124.9 GiB Borderline with 8 cards. Doesn't fit
MiMo-V2.6-Flash-RL 309B (14.8B active) Q2_K 124.9 GiB Borderline with 8 cards. Doesn't fit
K-EXAONE-236B-A23B 237B (22.7B active) IQ4_XS 126.3 GiB Borderline with 8 cards. Doesn't fit
GLM-4.5 353B (32.9B active) Q2_K 130.7 GiB Borderline with 8 cards. Doesn't fit
GLM-4.7 353B (32.9B active) Q2_K 130.7 GiB Borderline with 8 cards. Doesn't fit
Qwen3-Coder-REAP-363B-A35B 363B (34.5B active) Q2_K 132.7 GiB Borderline with 8 cards. Doesn't fit
Qwen3-235B-A22B 235B (21.6B active) Q4_K_M 141.9 GiB Borderline with 8 cards. Doesn't fit
Qwen3-Coder-480B-A35B-Instruct 480B (34.5B active) Q2_K 174.3 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3.5-397B-A17B 396B (16.3B active) Q3_K_M 175.6 GiB Does not fit even on 8 cards. Doesn't fit
GLM-5.1 744B (40.8B active) IQ2_XXS 197.6 GiB Does not fit even on 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 16 GB