DeskGPU
English

NVIDIA GeForce RTX 3090: 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 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
936 GB/s
Board power (TDP)
350 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): 21.44 GiB per card = 24 GiB nominal − 453 MiB (nominal minus the total that llama.cpp reported for this GPU in public logs) − 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 apply to the configuration seen in public logs, where llama.cpp reported 24,123 MiB of total memory for this GPU. 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) IQ3_XXS 21.2 GiB 20,736 ≤ 193 tok/s Fits
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) IQ3_XXS 20.0 GiB 148,992 ≤ 660 tok/s Fits
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) IQ3_XXS 20.7 GiB 83,968 ≤ 544 tok/s Fits
Hermes-4.3-36B 36.2B Q3_K_M 20.4 GiB 12,288 ≤ 48.2 tok/s Fits
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) Q4_0 20.9 GiB 58,112 ≤ 479 tok/s Fits
Holo-3.1-35B-A3B 34.7B (2.9B active) IQ4_XS 20.2 GiB 62,720 ≤ 458 tok/s Fits
Holo3-35B-A3B 34.7B (2.9B active) IQ4_XS 20.2 GiB 62,720 ≤ 458 tok/s Fits
Holo4-35B-A3B 34.7B (2.9B active) Q4_0 21.2 GiB 18,944 ≤ 430 tok/s Fits
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) Q4_0 21.1 GiB 25,344 ≤ 460 tok/s Fits
KAT-Coder-V2.5-Dev 34.7B (2.9B active) Q4_0 21.2 GiB 18,944 ≤ 430 tok/s Fits
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB 184,064 ≤ 359 tok/s Fits
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) Q4_0 21.1 GiB 25,344 ≤ 460 tok/s Fits
Qwen3.6-35B-A3B 34.7B (2.9B active) Q4_0 21.2 GiB 19,200 ≤ 430 tok/s Fits
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) Q4_0 21.0 GiB 29,184 ≤ 461 tok/s Fits
Laguna-XS-2.1 33.4B (2.8B active) Q4_0 20.6 GiB 27,136 ≤ 405 tok/s Fits
DeepSeek-R1-Distill-Qwen-32B 32.8B Q3_K_M 18.7 GiB 18,688 ≤ 52.8 tok/s Fits
Qwen2.5-32B-Instruct 32.8B Q4_0 21.3 GiB 8,704 ≤ 46.0 tok/s Fits
Qwen2.5-Coder-32B-Instruct 32.8B Q4_0 21.3 GiB 8,704 ≤ 46.0 tok/s Fits
AesCode-32B 32.8B IQ4_XS 20.8 GiB 10,496 ≤ 47.2 tok/s Fits
Cosmos-Reason2-32B 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
FrogBoss-32B-2510 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
Nemotron-Terminal-32B 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
Qwen3-VL-32B-Instruct 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
Qwen3-VL-32B-Thinking 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
SERA-32B 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
WebWorld-32B 32.8B Q4_0 21.3 GiB 8,448 ≤ 45.9 tok/s Fits
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB 12,032 ≤ 50.2 tok/s Fits
Olmo-3.1-32B-Instruct 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3.1-32B-Instruct-DPO 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3.1-32B-Think 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3-1125-32B 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3-32B-Think 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3-32B-Think-DPO 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Olmo-3-32B-Think-SFT 32.2B Q4_0 21.1 GiB 9,472 ≤ 48.3 tok/s Fits
Holotron4-30B-A3B 31.6B (3.2B active) Q4_0 19.0 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 451 tok/s Fits
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) Q4_0 19.2 GiB 262,144 ≤ 408 tok/s Fits
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q4_0 19.0 GiB 262,144 ≤ 451 tok/s Fits
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.3 GiB 262,144 ≤ 408 tok/s Fits
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.2 GiB 262,144 ≤ 419 tok/s Fits
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) Q4_0 19.0 GiB 262,144 ≤ 451 tok/s Fits
gemma-4-31B 30.7B Q3_K_M 20.9 GiB 14,848 ≤ 55.8 tok/s Fits
gemma-4-31B-it 30.7B Q3_K_M 20.3 GiB 21,248 ≤ 57.7 tok/s Fits
Ising-Calibration-1.5-31B-BF16 30.7B IQ3_XXS 18.6 GiB 42,240 ≤ 64.7 tok/s Fits
Holo2-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 21,504 ≤ 343 tok/s Fits
North-Mini-Code-1.0 30.5B (3.3B active) Q4_K_M 20.7 GiB 14,848 ≤ 335 tok/s Fits
GLM-4.7-Flash 29.9B (3.6B active) Q4_K_M 19.5 GiB 42,752 ≤ 329 tok/s Fits
granite-4.2-30b 29.3B Q4_K_M 20.5 GiB 11,520 ≤ 47.7 tok/s Fits
granite-4.1-30b 28.9B Q4_K_M 20.5 GiB 11,520 ≤ 47.7 tok/s Fits
Muse-Glimmer-30B 27.9B Q5_K_M 20.7 GiB 58,368 ≤ 48.4 tok/s Fits
gemma-2-27b-it 27.2B Q4_K_M 20.9 GiB 8,192 ≤ 49.4 tok/s Fits
gemma-3-27b-it 27.0B Q4_K_M 20.3 GiB 21,248 ≤ 53.0 tok/s Fits
translategemma-27b-it 27.0B Q4_K_M 20.3 GiB 21,248 ≤ 53.0 tok/s Fits
Fara1.5-27B 26.9B Q4_K_M 19.1 GiB 42,752 ≤ 54.0 tok/s Fits
Holo4-27B 26.9B Q5_K_M 20.6 GiB 19,968 ≤ 49.6 tok/s Fits
Qwen3.5-27B 26.9B Q5_K_M 21.0 GiB 14,592 ≤ 48.6 tok/s Fits
Qwen3.6-27B 26.9B Q5_K_M 20.9 GiB 15,872 ≤ 48.8 tok/s Fits
Qwen3.8-27B 26.9B Q4_K_M 18.8 GiB 47,616 ≤ 55.0 tok/s Fits
Qwen3.8-3.6-27B-blend 26.9B Q4_K_M 18.8 GiB 47,616 ≤ 55.0 tok/s Fits
UI-Mate-27B 26.9B Q4_K_M 19.1 GiB 42,752 ≤ 54.0 tok/s Fits
UI-Mate-democua-27B 26.9B Q5_K_M 20.6 GiB 19,968 ≤ 49.6 tok/s Fits
Trinity-Mini 26.1B (3.1B active) Q5_K_M 19.9 GiB 89,088 ≤ 368 tok/s Fits
Trinity-Mini-Base 26.1B (3.1B active) Q5_K_M 19.9 GiB 93,440 ≤ 380 tok/s Fits
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) Q5_K_M 19.6 GiB 4,096 ≤ 391 tok/s Fits
gemma-4-26B-A4B 25.2B (3.8B active) Q5_K_M 21.4 GiB 10,496 ≤ 285 tok/s Fits
gemma-4-26B-A4B-it 25.2B (3.8B active) Q4_K_M 19.3 GiB 103,680 ≤ 291 tok/s Fits
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) Q5_K_M 19.3 GiB 30,208 ≤ 309 tok/s Fits
LFM2.5-24B-A2B 24.0B (2.5B active) Q6_K 20.7 GiB 39,680 ≤ 426 tok/s Fits
LFM2-24B-A2B 23.8B (2.3B active) Q6_K 20.6 GiB 44,288 ≤ 447 tok/s Fits
Devstral-Small-2-24B-Instruct-2512 23.6B Q6_K 21.0 GiB 10,752 ≤ 46.5 tok/s Fits
Mistral-Small-3.2-24B-Instruct-2506 23.6B Q6_K 21.0 GiB 10,752 ≤ 46.5 tok/s Fits
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q6_K 20.1 GiB 32,000 ≤ 268 tok/s Fits
EuroLLM-22B-2512 22.6B Q6_K 20.6 GiB 11,776 ≤ 47.4 tok/s Fits
EuroLLM-22B-Instruct-2512 22.6B Q6_K 20.6 GiB 11,776 ≤ 47.4 tok/s Fits
gpt-oss-20b 20.9B (3.6B active) Q8_0 12.9 GiB 131,072 ≤ 337 tok/s Fits
OptiMind-SFT 20.9B (3.6B active) Q5_K_M 17.8 GiB 131,072 ≤ 291 tok/s Fits
DeepSeek-R1-Distill-Qwen-14B 14.8B Q8_0 17.5 GiB 28,416 ≤ 56.8 tok/s Fits
Qwen2.5-14B-Instruct 14.8B Q8_0 17.5 GiB 28,416 ≤ 56.8 tok/s Fits
ContextPilot-14B 14.8B Q8_0 17.2 GiB 34,048 ≤ 57.7 tok/s Fits
FrogMini-14B-2510 14.8B Q6_K 13.9 GiB 40,960 ≤ 73.0 tok/s Fits
JanusCoder-14B 14.8B Q8_0 17.2 GiB 32,768 ≤ 57.7 tok/s Fits
Nemotron-Cascade-14B-Thinking 14.8B Q8_0 17.2 GiB 32,768 ≤ 57.7 tok/s Fits
Nemotron-Terminal-14B 14.8B Q6_K 13.9 GiB 40,960 ≤ 73.0 tok/s Fits
NousCoder-14B 14.8B Q8_0 17.2 GiB 34,048 ≤ 57.7 tok/s Fits
Qwen3-14B 14.8B Q8_0 17.2 GiB 34,048 ≤ 57.7 tok/s Fits
Qwen3-Nemotron-14B-BRRM 14.8B Q6_K 13.9 GiB 40,960 ≤ 73.0 tok/s Fits
WebWorld-14B 14.8B Q6_K 13.9 GiB 40,960 ≤ 73.0 tok/s Fits
phi-4 14.7B Q8_0 17.7 GiB 16,384 ≤ 56.0 tok/s Fits
Apriel-1.6-15b-Thinker 14.4B Q8_0 17.2 GiB 29,952 ≤ 57.7 tok/s Fits
Ministral-3-14B-Instruct-2512 13.5B Q8_0 16.0 GiB 41,728 ≤ 62.5 tok/s Fits
Ministral-3-14B-Reasoning-2512 13.5B Q8_0 16.0 GiB 41,728 ≤ 62.5 tok/s Fits
Mistral-Nemo-Instruct-2407 12.2B Q8_0 14.7 GiB 49,664 ≤ 68.6 tok/s Fits
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 371 tok/s Fits
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 445 tok/s Fits
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 371 tok/s Fits
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 445 tok/s Fits
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) Q8_0 14.0 GiB 131,072 ≤ 371 tok/s Fits
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) Q6_K 12.1 GiB 131,072 ≤ 445 tok/s Fits
gemma-4-12B 11.9B Q8_0 15.6 GiB 262,144 ≤ 71.3 tok/s Fits
gemma-4-12B-it 11.9B Q8_0 15.6 GiB 262,144 ≤ 71.3 tok/s Fits
gemma-3-12b-it 11.8B Q8_0 15.8 GiB 92,928 ≤ 70.0 tok/s Fits
translategemma-12b-it 11.8B Q8_0 15.8 GiB 92,928 ≤ 70.0 tok/s Fits
Bielik-11B-v3.0-Instruct 11.2B Q8_0 14.4 GiB 32,768 ≤ 69.8 tok/s Fits
AutoGLM-Phone-9B 9.4B F16 18.9 GiB 65,536 ≤ 52.3 tok/s Fits
AutoGLM-Phone-9B-Multilingual 9.4B Q6_K 9.2 GiB 65,536 ≤ 116 tok/s Fits
GLM-4.6V-Flash 9.4B BF16 18.9 GiB 69,120 ≤ 52.3 tok/s Fits
gemma-2-9b-it 9.2B Q8_0 14.8 GiB 8,192 ≤ 73.2 tok/s Fits
EuroLLM-9B-Instruct-2512 9.2B F16 19.6 GiB 18,944 ≤ 50.1 tok/s Fits
Fara1.5-9B 9.0B BF16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
Holo-3.1-9B 9.0B F16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
MiMo-V2.6-Distill-Qwen-9B 9.0B BF16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
Qwen3.5-9B 9.0B BF16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
Qwen3.5-9B-Base 9.0B F16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
UI-Mate-9B 9.0B BF16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
UI-Venus-2-9B 9.0B BF16 17.5 GiB 122,112 ≤ 58.0 tok/s Fits
NVIDIA-Nemotron-Nano-9B-v2 8.9B BF16 18.3 GiB 131,072 ≤ 55.9 tok/s Fits
granite-4.1-8b 8.8B BF16 19.0 GiB 22,784 ≤ 51.7 tok/s Fits
granite-4.2-8b 8.8B BF16 19.0 GiB 22,784 ≤ 51.7 tok/s Fits
Ministral-3-8B-Instruct-2512 8.5B BF16 18.0 GiB 33,024 ≤ 54.9 tok/s Fits
Ministral-3-8B-Reasoning-2512 8.5B BF16 18.0 GiB 33,024 ≤ 54.9 tok/s Fits
LFM2.5-8B-A1B 8.5B (1.7B active) BF16 18.0 GiB 128,000 ≤ 269 tok/s Fits
granite-guardian-4.1-8b 8.4B BF16 19.0 GiB 22,784 ≤ 51.7 tok/s Fits
LFM2-8B-A1B 8.3B (1.6B active) F16 17.7 GiB 128,000 ≤ 291 tok/s Fits
rnj-1-instruct 8.3B BF16 18.6 GiB 29,696 ≤ 52.9 tok/s Fits
AesCode-8B 8.2B BF16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
ArmorOCR 8.2B Q8_0 10.4 GiB 83,456 ≤ 101 tok/s Fits
AstaBrief_8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 126 tok/s Fits
ContextPilot-8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 126 tok/s Fits
Cosmos-Reason2-8B 8.2B Q6_K 8.6 GiB 95,744 ≤ 126 tok/s Fits
DeepSeek-R1-0528-Qwen3-8B 8.2B BF16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
Holo2-8B 8.2B Q6_K 8.6 GiB 95,744 ≤ 126 tok/s Fits
intent-aware-lfqa-qwen3-8b-baseline 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
intent-aware-lfqa-qwen3-8b-multiview 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
JanusCoder-8B 8.2B BF16 17.3 GiB 32,768 ≤ 57.3 tok/s Fits
MathForm-8B 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
Nemotron-Cascade-8B 8.2B BF16 17.3 GiB 32,768 ≤ 57.3 tok/s Fits
Nemotron-Cascade-8B-Thinking 8.2B BF16 17.3 GiB 32,768 ≤ 57.3 tok/s Fits
Nemotron-Orchestrator-8B 8.2B BF16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
Nemotron-Terminal-8B 8.2B Q6_K 8.6 GiB 40,960 ≤ 126 tok/s Fits
Qwen3-8B 8.2B Q8_0 10.4 GiB 40,960 ≤ 101 tok/s Fits
Qwen3-Nemotron-8B-BRRM 8.2B Q6_K 8.6 GiB 40,960 ≤ 126 tok/s Fits
Qwen3-VL-8B-Instruct 8.2B BF16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
Qwen3-VL-8B-Thinking 8.2B BF16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
RLVR-8B-0926 8.2B Q6_K 8.6 GiB 95,744 ≤ 126 tok/s Fits
Step3-VL-10B-Base 8.2B Q6_K 8.6 GiB 40,960 ≤ 126 tok/s Fits
UI-Venus-1.5-8B 8.2B Q6_K 8.6 GiB 95,744 ≤ 126 tok/s Fits
WebWorld-8B 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
ZwZ-8B 8.2B Q6_K 8.6 GiB 95,744 ≤ 126 tok/s Fits
MiniCPM-o-4_5 8.2B F16 17.3 GiB 36,096 ≤ 57.3 tok/s Fits
granite-3.3-8b-instruct 8.2B F16 18.6 GiB 25,344 ≤ 52.9 tok/s Fits
granite-guardian-3.2-8b-factuality-detection 8.2B F16 18.6 GiB 25,344 ≤ 52.9 tok/s Fits
intent-aware-lfqa-llama3-8b-baseline 8.0B F16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B F16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B F16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
intent-aware-lfqa-llama3-8b-multiview 8.0B F16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
DeepSeek-R1-Distill-Llama-8B 8.0B BF16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
HARC-Llama-3.1-8B-Instruct 8.0B Q6_K 8.4 GiB 108,288 ≤ 129 tok/s Fits
Llama-3.1-8B-Instruct 8.0B BF16 17.0 GiB 41,728 ≤ 58.2 tok/s Fits
AprielGuard 7.9B Q6_K 7.9 GiB 131,072 ≤ 139 tok/s Fits
MiMo-Embodied-7B 7.6B Q6_K 8.1 GiB 98,816 ≤ 135 tok/s Fits
DeepSeek-R1-Distill-Qwen-7B 7.6B F16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
Fara-7B 7.6B BF16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
HARC-Qwen2.5-7B-Instruct 7.6B Q6_K 7.5 GiB 32,768 ≤ 149 tok/s Fits
JanusCoderV-7B 7.6B BF16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
olmOCR-2-7B-1025 7.6B BF16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
Qwen2.5-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 117 tok/s Fits
Qwen2.5-Coder-7B-Instruct 7.6B Q8_0 9.1 GiB 32,768 ≤ 117 tok/s Fits
Qwen2.5-VL-7B-Instruct 7.6B BF16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
Qwen2.5-VL-7B-Surg-CholecT50 7.6B F16 15.6 GiB 107,520 ≤ 64.1 tok/s Fits
Spatial-SSRL-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 149 tok/s Fits
X-Reasoner-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 149 tok/s Fits
ZwZ-7B 7.6B Q6_K 7.5 GiB 128,000 ≤ 149 tok/s Fits
gemma-4-E4B 7.5B F16 11.0 GiB 131,072 ≤ 98.0 tok/s Fits
gemma-4-E4B-it 7.5B BF16 11.0 GiB 131,072 ≤ 98.0 tok/s Fits
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q8_0 10.2 GiB 32,768 ≤ 102 tok/s Fits
ContextPilot-E4B 7.5B F16 10.9 GiB 131,072 ≤ 99.1 tok/s Fits
Olmo-3.1-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3.1-7B-RL-Zero-Math 7.3B F16 19.0 GiB 12,800 ≤ 56.9 tok/s Fits
Olmo-3-7B-Instruct 7.3B BF16 19.0 GiB 12,800 ≤ 56.9 tok/s Fits
Olmo-3-7B-Instruct-DPO 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-Instruct-SFT 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-RL-Zero-General 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-RL-Zero-IF 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-RL-Zero-Math 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-RL-Zero-Mix 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-Think 7.3B BF16 19.0 GiB 12,800 ≤ 56.9 tok/s Fits
Olmo-3-7B-Think-DPO 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Olmo-3-7B-Think-SFT 7.3B Q6_K 11.0 GiB 61,952 ≤ 112 tok/s Fits
Mistral-7B-Instruct-v0.2 7.2B Q6_K 8.1 GiB 32,768 ≤ 136 tok/s Fits
Trinity-Nano-Base 6.1B (819M active) Q6_K 6.7 GiB 131,072 ≤ 1,039 tok/s Fits
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) Q6_K 6.4 GiB 4,096 ≤ 1,112 tok/s Fits
Trinity-Nano-Preview 6.1B (819M active) BF16 13.5 GiB 131,072 ≤ 504 tok/s Fits
Youtu-VL-4B-Instruct 4.9B Q6_K 5.9 GiB 32,768 ≤ 212 tok/s Fits
Holo-3.1-4B 4.8B F16 10.2 GiB 262,144 ≤ 108 tok/s Fits
gemma-4-E2B 4.6B Q6_K 3.5 GiB 131,072 ≤ 478 tok/s Fits
gemma-4-E2B-it 4.6B BF16 6.1 GiB 131,072 ≤ 201 tok/s Fits
AgentCPM-Explore 4.4B Q6_K 5.7 GiB 115,200 ≤ 208 tok/s Fits
CapRL-Qwen3VL-4B 4.4B F16 10.4 GiB 83,456 ≤ 101 tok/s Fits
Holo2-4B 4.4B F16 10.4 GiB 83,456 ≤ 101 tok/s Fits
intent-aware-lfqa-qwen3-4b-baseline 4.4B F16 10.4 GiB 40,960 ≤ 101 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B F16 10.4 GiB 40,960 ≤ 101 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B F16 10.4 GiB 40,960 ≤ 101 tok/s Fits
intent-aware-lfqa-qwen3-4b-multiview 4.4B F16 10.4 GiB 40,960 ≤ 101 tok/s Fits
Spatial-SSRL-Qwen3VL-4B 4.4B F16 10.4 GiB 83,456 ≤ 101 tok/s Fits
ZwZ-4B 4.4B Q6_K 5.7 GiB 115,200 ≤ 208 tok/s Fits
Fara1.5-4B 4.2B BF16 10.2 GiB 262,144 ≤ 108 tok/s Fits
FrogNano-4B-2609 4.2B BF16 10.2 GiB 262,144 ≤ 108 tok/s Fits
Qwen3.5-4B 4.2B BF16 10.2 GiB 262,144 ≤ 108 tok/s Fits
Qwen3.5-4B-Base 4.2B F16 10.2 GiB 262,144 ≤ 108 tok/s Fits
UserRepGen-4B 4.2B BF16 10.2 GiB 262,144 ≤ 108 tok/s Fits
Riva-Translate-4B-Instruct-v1.1 4.2B Q6_K 6.0 GiB 8,192 ≤ 195 tok/s Fits
GELab-Zero-4B-preview 4.0B BF16 10.4 GiB 83,456 ≤ 101 tok/s Fits
Qwen3-4B 4.0B Q8_0 6.7 GiB 40,960 ≤ 171 tok/s Fits
Qwen3-4B-Instruct-2507 4.0B F16 10.4 GiB 83,456 ≤ 101 tok/s Fits
Qwen3-VL-4B-Instruct 4.0B BF16 10.4 GiB 83,456 ≤ 101 tok/s Fits
Qwen3-VL-4B-Thinking 4.0B BF16 10.4 GiB 83,456 ≤ 101 tok/s Fits
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B BF16 8.7 GiB 262,144 ≤ 129 tok/s Fits
gemma-3-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 116 tok/s Fits
medgemma-1.5-4b-it 3.9B BF16 9.9 GiB 131,072 ≤ 116 tok/s Fits
Nemotron-3-Content-Safety 3.9B Q6_K 5.4 GiB 131,072 ≤ 269 tok/s Fits
translategemma-4b-it 3.9B F16 9.9 GiB 131,072 ≤ 116 tok/s Fits
Phi-4-mini-instruct 3.8B BF16 10.0 GiB 95,744 ≤ 107 tok/s Fits
Apertus-v1.1-4B 3.8B Q6_K 4.4 GiB 4,096 ≤ 292 tok/s Fits
Phi-3.5-mini-instruct 3.8B Q8_0 8.3 GiB 41,984 ≤ 130 tok/s Fits
granite-4.2-3b 3.7B BF16 8.6 GiB 131,072 ≤ 125 tok/s Fits
BitCPM-CANN-3B-unquantized 3.6B Q6_K 4.3 GiB 32,768 ≤ 305 tok/s Fits
kanana-2-3b-instruct 3.5B F16 8.6 GiB 32,768 ≤ 126 tok/s Fits
Ministral-3-3B-Instruct-2512 3.4B BF16 8.9 GiB 126,208 ≤ 121 tok/s Fits
Ministral-3-3B-Reasoning-2512 3.4B BF16 8.9 GiB 126,208 ≤ 121 tok/s Fits
granite-vision-4.1-4b 3.4B BF16 8.6 GiB 131,072 ≤ 125 tok/s Fits
granite-4.1-3b 3.4B BF16 8.6 GiB 131,072 ≤ 125 tok/s Fits
granite-guardian-4.0-3b-toxicity-ja 3.4B Q6_K 4.7 GiB 131,072 ≤ 270 tok/s Fits
Qwen2.5-3B-Instruct 3.4B Q8_0 4.8 GiB 32,768 ≤ 261 tok/s Fits
tiny-aya-earth 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 132 tok/s Fits
tiny-aya-fire 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 132 tok/s Fits
tiny-aya-global 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 132 tok/s Fits
tiny-aya-water 3.3B BF16 8.7 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 132 tok/s Fits
Llama-3.2-3B-Instruct 3.2B BF16 8.5 GiB 121,088 ≤ 127 tok/s Fits
AI21-Jamba-Reasoning-3B 3.2B BF16 7.3 GiB 262,144 ≤ 154 tok/s Fits
AI21-Jamba2-3B 3.2B BF16 7.3 GiB 262,144 ≤ 154 tok/s Fits
kanana-2-3b-base 3.2B Q6_K 4.9 GiB 32,768 ≤ 254 tok/s Fits
SmolLM3-3B 3.1B BF16 7.9 GiB 65,536 ≤ 139 tok/s Fits
SmolLM3-3B-GSM8K-SFT 3.1B Q6_K 4.3 GiB 65,536 ≤ 299 tok/s Fits
LFM2-2.6B-Exp 2.7B F16 6.5 GiB 128,000 ≤ 177 tok/s Fits
d1-3B 2.7B BF16 6.7 GiB 32,768 ≤ 169 tok/s Fits
LFM2.5-2.6B 2.7B BF16 6.7 GiB 131,072 ≤ 169 tok/s Fits
LFM2.5-2.6B-Base 2.7B Q6_K 3.6 GiB 128,000 ≤ 399 tok/s Fits
LFM2.5-VL-3B 2.7B BF16 6.7 GiB 32,768 ≤ 169 tok/s Fits
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) Q6_K 3.6 GiB 32,768 ≤ 1,523 tok/s Fits
LFM2-2.6B-Longevity 2.6B F16 6.5 GiB 128,000 ≤ 177 tok/s Fits
LFM2-2.6B-Transcript 2.6B BF16 6.5 GiB 128,000 ≤ 177 tok/s Fits
LFM2-VL-3B 2.6B BF16 6.5 GiB 128,000 ≤ 177 tok/s Fits
MiniCPM5-2B 2.5B BF16 6.0 GiB 131,072 ≤ 193 tok/s Fits
MiniCPM5-2B-Base 2.5B Q6_K 3.4 GiB ≥ 262,144 (longer contexts not checked against measured logs) ≤ 426 tok/s Fits
CapRL-Qwen3VL-2B 2.0B F16 5.6 GiB 146,432 ≤ 214 tok/s Fits
HiPO-1.7B 2.0B Q6_K 3.6 GiB 40,960 ≤ 398 tok/s Fits
UI-Venus-1.5-2B 2.0B F16 5.6 GiB 146,432 ≤ 214 tok/s Fits
ZwZ-2B 2.0B F16 5.6 GiB 146,432 ≤ 214 tok/s Fits
Youtu-LLM-2B 2.0B Q6_K 3.2 GiB 131,072 ≤ 488 tok/s Fits
Youtu-LLM-2B-Base 2.0B Q6_K 3.2 GiB 131,072 ≤ 488 tok/s Fits
Qwen3.5-2B 1.9B BF16 5.4 GiB 262,144 ≤ 242 tok/s Fits
Qwen3.5-2B-Base 1.9B Q6_K 3.2 GiB 262,144 ≤ 569 tok/s Fits
Qwen3-1.7B 1.7B BF16 5.6 GiB 40,960 ≤ 214 tok/s Fits
Qwen3-VL-2B-Instruct 1.7B BF16 5.6 GiB 146,432 ≤ 214 tok/s Fits
Qwen3-VL-2B-Thinking 1.7B BF16 5.6 GiB 146,432 ≤ 214 tok/s Fits
SingGuard-2b 1.7B F16 5.6 GiB 146,432 ≤ 214 tok/s Fits
granite-4.0-1b 1.6B BF16 5.1 GiB 131,072 ≤ 238 tok/s Fits
Apertus-v1.1-1.5B 1.5B F16 3.8 GiB 4,096 ≤ 358 tok/s Fits
Apertus-v1.1-1.5B-Instruct 1.5B F16 3.8 GiB 4,096 ≤ 358 tok/s Fits
granite-4.0-h-1b 1.5B BF16 4.4 GiB 131,072 ≤ 313 tok/s Fits
Llama-3.2-1B-Instruct 1.2B BF16 4.0 GiB 131,072 ≤ 342 tok/s Fits
LFM2.5-1.2B-Base 1.2B BF16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-1.2B-Instruct 1.2B BF16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-1.2B-JP 1.2B F16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-1.2B-JP-202606 1.2B F16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-1.2B-Thinking 1.2B BF16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-VL-1.6B 1.2B BF16 3.7 GiB 128,000 ≤ 383 tok/s Fits
LFM2.5-VL-1.6B-Extract 1.2B F16 3.7 GiB 128,000 ≤ 383 tok/s Fits
MiniCPM5-1B 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,014 tok/s Fits
MiniCPM5-1B-Base 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,014 tok/s Fits
MiniCPM5-1B-SFT 1.1B Q6_K 2.2 GiB 131,072 ≤ 1,014 tok/s Fits
Holo-3.1-0.8B 1.0B Q6_K 2.3 GiB 262,144 ≤ 1,301 tok/s Fits
MiniCPM-V-4.7-1B 1.0B F16 3.2 GiB 262,144 ≤ 583 tok/s Fits
gemma-3-1b-it 1.0B BF16 3.6 GiB 32,768 ≤ 458 tok/s Fits
Qwen3.5-0.8B 752M BF16 3.2 GiB 262,144 ≤ 583 tok/s Fits
Qwen3.5-0.8B-Base 752M Q6_K 2.3 GiB 262,144 ≤ 1,301 tok/s Fits
MiniCPM-V-4.6 752M F16 3.2 GiB 262,144 ≤ 583 tok/s Fits
MiniCPM-V-4.6-Thinking 752M F16 3.2 GiB 262,144 ≤ 583 tok/s Fits
Qwen3-0.6B 752M BF16 3.4 GiB 40,960 ≤ 439 tok/s Fits
HunyuanOCR 539M F16 3.1 GiB 32,768 ≤ 497 tok/s Fits
LFM2.5-350M 354M BF16 2.1 GiB 128,000 ≤ 1,156 tok/s Fits
LFM2.5-Encoder-350M-Diffusion 354M Q6_K 1.7 GiB 128,000 ≤ 2,390 tok/s Fits
LFM2.5-VL-450M 354M BF16 2.1 GiB 128,000 ≤ 1,156 tok/s Fits
LFM2.5-VL-450M-Extract 354M F16 2.1 GiB 128,000 ≤ 1,156 tok/s Fits
granite-4.0-350m 352M BF16 2.2 GiB 32,768 ≤ 996 tok/s Fits
granite-4.0-h-350m 340M BF16 2.1 GiB 32,768 ≤ 1,309 tok/s Fits
functiongemma-270m-it 268M BF16 2.1 GiB 32,768 ≤ 1,644 tok/s Fits
LFM2.5-230M 230M BF16 1.8 GiB 128,000 ≤ 1,671 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

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 5 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 7 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

Detailed pages for this GPU

Other devices with 24 GB