DeskGPU
English

NVIDIA GeForce RTX 3080 10GB: 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 3080 10GB has 10 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)
10 GB
Memory type
GDDR6X
Memory bus width
320 bit
Memory bandwidth
760 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): 6.88 GiB per card = 10 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 10 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
FrogMini-14B-2510 14.8B IQ2_XXS 6.6 GiB 9,728 ≤ 141 tok/s Fits
Nemotron-Terminal-14B 14.8B IQ2_XXS 6.6 GiB 9,728 ≤ 141 tok/s Fits
Qwen3-Nemotron-14B-BRRM 14.8B IQ2_XXS 6.6 GiB 9,728 ≤ 141 tok/s Fits
WebWorld-14B 14.8B IQ2_XXS 6.6 GiB 9,728 ≤ 141 tok/s Fits
Mistral-Nemo-Instruct-2407 12.2B IQ2_M 6.7 GiB 9,472 ≤ 139 tok/s Fits
Mellum2-12B-A2.5B-Base 12.1B (2.2B active) IQ3_XXS 6.8 GiB 12,288 ≤ 646 tok/s Fits
Mellum2-12B-A2.5B-Instruct 12.1B (2.2B active) Q2_K 6.6 GiB 26,368 ≤ 585 tok/s Fits
Mellum2-12B-A2.5B-Instruct-SFT 12.1B (2.2B active) IQ3_XXS 6.8 GiB 12,288 ≤ 646 tok/s Fits
Mellum2-12B-A2.5B-Thinking 12.1B (2.2B active) Q2_K 6.6 GiB 26,368 ≤ 585 tok/s Fits
Mellum2-12B-A2.5B-Thinking-SFT 12.1B (2.2B active) IQ3_XXS 6.8 GiB 12,288 ≤ 646 tok/s Fits
AutoGLM-Phone-9B 9.4B IQ4_XS 6.5 GiB 16,384 ≤ 143 tok/s Fits
AutoGLM-Phone-9B-Multilingual 9.4B Q4_0 6.7 GiB 13,056 ≤ 139 tok/s Fits
GLM-4.6V-Flash 9.4B Q4_0 6.7 GiB 13,056 ≤ 139 tok/s Fits
EuroLLM-9B-Instruct-2512 9.2B Q2_K 6.0 GiB 13,056 ≤ 157 tok/s Fits
Fara1.5-9B 9.0B Q4_0 6.8 GiB 10,496 ≤ 147 tok/s Fits
Holo-3.1-9B 9.0B IQ4_XS 6.6 GiB 16,896 ≤ 154 tok/s Fits
MiMo-V2.6-Distill-Qwen-9B 9.0B Q4_0 6.8 GiB 10,496 ≤ 147 tok/s Fits
Qwen3.5-9B 9.0B Q4_0 6.7 GiB 13,568 ≤ 150 tok/s Fits
Qwen3.5-9B-Base 9.0B IQ4_XS 6.6 GiB 16,896 ≤ 154 tok/s Fits
UI-Mate-9B 9.0B Q4_0 6.8 GiB 10,496 ≤ 147 tok/s Fits
UI-Venus-2-9B 9.0B Q4_0 6.8 GiB 10,496 ≤ 147 tok/s Fits
NVIDIA-Nemotron-Nano-9B-v2 8.9B IQ4_XS 6.8 GiB 11,520 ≤ 150 tok/s Fits
granite-4.1-8b 8.8B Q3_K_M 6.7 GiB 9,216 ≤ 138 tok/s Fits
granite-4.2-8b 8.8B Q3_K_M 6.7 GiB 9,216 ≤ 138 tok/s Fits
LFM2.5-8B-A1B 8.5B (1.7B active) Q4_K_M 6.4 GiB 39,936 ≤ 651 tok/s Fits
granite-guardian-4.1-8b 8.4B Q3_K_M 6.7 GiB 9,216 ≤ 138 tok/s Fits
LFM2-8B-A1B 8.3B (1.6B active) Q4_K_M 6.3 GiB 47,360 ≤ 715 tok/s Fits
rnj-1-instruct 8.3B IQ4_XS 6.8 GiB 8,448 ≤ 134 tok/s Fits
AesCode-8B 8.2B IQ4_XS 6.8 GiB 8,704 ≤ 137 tok/s Fits
AstaBrief_8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
ContextPilot-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Cosmos-Reason2-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
DeepSeek-R1-0528-Qwen3-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Holo2-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
intent-aware-lfqa-qwen3-8b-baseline 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-explicit 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-8b-intent-implicit 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-8b-multiview 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
JanusCoder-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
MathForm-8B 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
Nemotron-Cascade-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Nemotron-Cascade-8B-Thinking 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Nemotron-Orchestrator-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Nemotron-Terminal-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Qwen3-Nemotron-8B-BRRM 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Qwen3-VL-8B-Instruct 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Qwen3-VL-8B-Thinking 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
RLVR-8B-0926 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
Step3-VL-10B-Base 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
UI-Venus-1.5-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
WebWorld-8B 8.2B IQ4_XS 6.7 GiB 9,472 ≤ 139 tok/s Fits
ZwZ-8B 8.2B Q4_0 6.8 GiB 8,192 ≤ 135 tok/s Fits
MiniCPM-o-4_5 8.2B Q4_0 6.8 GiB 8,448 ≤ 135 tok/s Fits
granite-3.3-8b-instruct 8.2B Q3_K_M 6.5 GiB 10,240 ≤ 142 tok/s Fits
granite-guardian-3.2-8b-factuality-detection 8.2B Q3_K_M 6.5 GiB 10,240 ≤ 142 tok/s Fits
intent-aware-lfqa-llama3-8b-baseline 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-explicit 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
intent-aware-lfqa-llama3-8b-intent-implicit 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
intent-aware-lfqa-llama3-8b-multiview 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
DeepSeek-R1-Distill-Llama-8B 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
HARC-Llama-3.1-8B-Instruct 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
Llama-3.1-8B-Instruct 8.0B Q4_K_M 6.9 GiB 8,192 ≤ 134 tok/s Fits
AprielGuard 7.9B Q4_K_M 6.5 GiB 12,288 ≤ 144 tok/s Fits
MiMo-Embodied-7B 7.6B Q4_K_M 6.7 GiB 8,960 ≤ 137 tok/s Fits
DeepSeek-R1-Distill-Qwen-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Fara-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
HARC-Qwen2.5-7B-Instruct 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
JanusCoderV-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
olmOCR-2-7B-1025 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Qwen2.5-7B-Instruct 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Qwen2.5-Coder-7B-Instruct 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Qwen2.5-VL-7B-Instruct 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Qwen2.5-VL-7B-Surg-CholecT50 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
Spatial-SSRL-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
X-Reasoner-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
ZwZ-7B 7.6B Q5_K_M 6.7 GiB 10,240 ≤ 137 tok/s Fits
gemma-4-E4B 7.5B Q8_0 6.7 GiB 17,408 ≤ 147 tok/s Fits
gemma-4-E4B-it 7.5B Q8_0 6.9 GiB 8,704 ≤ 142 tok/s Fits
ContextPilot-E4B 7.5B Q8_0 6.6 GiB 20,736 ≤ 149 tok/s Fits
Mistral-7B-Instruct-v0.2 7.2B Q4_K_M 6.5 GiB 10,496 ≤ 142 tok/s Fits
Trinity-Nano-Base 6.1B (819M active) Q6_K 6.7 GiB 19,200 ≤ 844 tok/s Fits
Trinity-Nano-Base-Pre-Anneal 6.1B (819M active) Q6_K 6.4 GiB 4,096 ≤ 903 tok/s Fits
Trinity-Nano-Preview 6.1B (819M active) Q6_K 6.7 GiB 18,176 ≤ 831 tok/s Fits
Youtu-VL-4B-Instruct 4.9B Q6_K 5.9 GiB 28,416 ≤ 172 tok/s Fits
Holo-3.1-4B 4.8B Q8_0 6.4 GiB 22,784 ≤ 160 tok/s Fits
gemma-4-E2B 4.6B Q6_K 3.5 GiB 131,072 ≤ 388 tok/s Fits
gemma-4-E2B-it 4.6B BF16 6.1 GiB 100,096 ≤ 163 tok/s Fits
AgentCPM-Explore 4.4B Q6_K 5.7 GiB 15,872 ≤ 169 tok/s Fits
CapRL-Qwen3VL-4B 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Holo2-4B 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-4b-baseline 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-explicit 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-4b-intent-implicit 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
intent-aware-lfqa-qwen3-4b-multiview 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Spatial-SSRL-Qwen3VL-4B 4.4B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
ZwZ-4B 4.4B Q6_K 5.7 GiB 15,872 ≤ 169 tok/s Fits
Fara1.5-4B 4.2B Q8_0 6.4 GiB 22,528 ≤ 160 tok/s Fits
FrogNano-4B-2609 4.2B Q8_0 6.4 GiB 22,528 ≤ 160 tok/s Fits
Qwen3.5-4B 4.2B Q8_0 6.4 GiB 22,784 ≤ 160 tok/s Fits
Qwen3.5-4B-Base 4.2B Q8_0 6.4 GiB 22,784 ≤ 160 tok/s Fits
UserRepGen-4B 4.2B Q8_0 6.4 GiB 22,528 ≤ 160 tok/s Fits
Riva-Translate-4B-Instruct-v1.1 4.2B Q6_K 6.0 GiB 8,192 ≤ 159 tok/s Fits
GELab-Zero-4B-preview 4.0B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Qwen3-4B 4.0B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Qwen3-4B-Instruct-2507 4.0B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Qwen3-VL-4B-Instruct 4.0B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
Qwen3-VL-4B-Thinking 4.0B Q8_0 6.7 GiB 9,216 ≤ 139 tok/s Fits
NVIDIA-Nemotron-3-Nano-4B-BF16 4.0B Q8_0 5.5 GiB 86,528 ≤ 194 tok/s Fits
gemma-3-4b-it 3.9B Q8_0 6.3 GiB 34,304 ≤ 172 tok/s Fits
medgemma-1.5-4b-it 3.9B Q8_0 6.3 GiB 34,304 ≤ 172 tok/s Fits
Nemotron-3-Content-Safety 3.9B Q6_K 5.4 GiB 76,032 ≤ 219 tok/s Fits
translategemma-4b-it 3.9B Q8_0 6.3 GiB 34,304 ≤ 172 tok/s Fits
Phi-4-mini-instruct 3.8B Q8_0 6.5 GiB 11,264 ≤ 148 tok/s Fits
Apertus-v1.1-4B 3.8B Q6_K 4.4 GiB 4,096 ≤ 237 tok/s Fits
Phi-3.5-mini-instruct 3.8B Q4_K_M 6.7 GiB 8,448 ≤ 137 tok/s Fits
granite-4.2-3b 3.7B Q8_0 5.5 GiB 25,088 ≤ 177 tok/s Fits
BitCPM-CANN-3B-unquantized 3.6B Q6_K 4.3 GiB 32,768 ≤ 247 tok/s Fits
kanana-2-3b-instruct 3.5B Q8_0 5.6 GiB 17,408 ≤ 171 tok/s Fits
Ministral-3-3B-Instruct-2512 3.4B Q8_0 5.7 GiB 18,944 ≤ 168 tok/s Fits
Ministral-3-3B-Reasoning-2512 3.4B Q8_0 5.7 GiB 18,944 ≤ 168 tok/s Fits
granite-vision-4.1-4b 3.4B Q8_0 5.5 GiB 25,088 ≤ 177 tok/s Fits
granite-4.1-3b 3.4B Q8_0 5.5 GiB 25,088 ≤ 177 tok/s Fits
granite-guardian-4.0-3b-toxicity-ja 3.4B Q6_K 4.7 GiB 34,816 ≤ 219 tok/s Fits
Qwen2.5-3B-Instruct 3.4B Q8_0 4.8 GiB 32,768 ≤ 212 tok/s Fits
tiny-aya-earth 3.3B Q8_0 5.6 GiB 45,312 ≤ 193 tok/s Fits
tiny-aya-fire 3.3B Q8_0 5.6 GiB 45,312 ≤ 193 tok/s Fits
tiny-aya-global 3.3B Q8_0 5.6 GiB 45,312 ≤ 193 tok/s Fits
tiny-aya-water 3.3B Q8_0 5.6 GiB 45,312 ≤ 193 tok/s Fits
Llama-3.2-3B-Instruct 3.2B Q8_0 5.5 GiB 19,712 ≤ 175 tok/s Fits
AI21-Jamba-Reasoning-3B 3.2B Q8_0 4.5 GiB 262,144 ≤ 235 tok/s Fits
AI21-Jamba2-3B 3.2B Q8_0 4.5 GiB 262,144 ≤ 235 tok/s Fits
kanana-2-3b-base 3.2B Q6_K 4.9 GiB 23,296 ≤ 206 tok/s Fits
SmolLM3-3B 3.1B Q8_0 5.1 GiB 32,256 ≤ 196 tok/s Fits
SmolLM3-3B-GSM8K-SFT 3.1B Q6_K 4.3 GiB 42,240 ≤ 243 tok/s Fits
LFM2-2.6B-Exp 2.7B F16 6.5 GiB 31,488 ≤ 144 tok/s Fits
d1-3B 2.7B BF16 6.7 GiB 17,664 ≤ 137 tok/s Fits
LFM2.5-2.6B 2.7B BF16 6.7 GiB 17,664 ≤ 137 tok/s Fits
LFM2.5-2.6B-Base 2.7B Q6_K 3.6 GiB 128,000 ≤ 324 tok/s Fits
LFM2.5-VL-3B 2.7B BF16 6.7 GiB 17,664 ≤ 137 tok/s Fits
EuroMoE-2.6B-A0.6B-Instruct-2512 2.6B (498M active) Q6_K 3.6 GiB 32,768 ≤ 1,236 tok/s Fits
LFM2-2.6B-Longevity 2.6B F16 6.5 GiB 31,488 ≤ 144 tok/s Fits
LFM2-2.6B-Transcript 2.6B BF16 6.5 GiB 31,488 ≤ 144 tok/s Fits
LFM2-VL-3B 2.6B BF16 6.5 GiB 31,488 ≤ 144 tok/s Fits
MiniCPM5-2B 2.5B BF16 6.0 GiB 27,136 ≤ 157 tok/s Fits
MiniCPM5-2B-Base 2.5B Q6_K 3.4 GiB 86,016 ≤ 346 tok/s Fits
CapRL-Qwen3VL-2B 2.0B F16 5.6 GiB 18,944 ≤ 173 tok/s Fits
HiPO-1.7B 2.0B Q6_K 3.6 GiB 36,352 ≤ 323 tok/s Fits
UI-Venus-1.5-2B 2.0B F16 5.6 GiB 18,944 ≤ 173 tok/s Fits
ZwZ-2B 2.0B F16 5.6 GiB 18,944 ≤ 173 tok/s Fits
Youtu-LLM-2B 2.0B Q6_K 3.2 GiB 105,472 ≤ 396 tok/s Fits
Youtu-LLM-2B-Base 2.0B Q6_K 3.2 GiB 105,472 ≤ 396 tok/s Fits
Qwen3.5-2B 1.9B BF16 5.4 GiB 114,176 ≤ 197 tok/s Fits
Qwen3.5-2B-Base 1.9B Q6_K 3.2 GiB 262,144 ≤ 462 tok/s Fits
Qwen3-1.7B 1.7B BF16 5.6 GiB 18,944 ≤ 173 tok/s Fits
Qwen3-VL-2B-Instruct 1.7B BF16 5.6 GiB 18,944 ≤ 173 tok/s Fits
Qwen3-VL-2B-Thinking 1.7B BF16 5.6 GiB 18,944 ≤ 173 tok/s Fits
SingGuard-2b 1.7B F16 5.6 GiB 18,944 ≤ 173 tok/s Fits
granite-4.0-1b 1.6B BF16 5.1 GiB 29,184 ≤ 193 tok/s Fits
Apertus-v1.1-1.5B 1.5B F16 3.8 GiB 4,096 ≤ 290 tok/s Fits
Apertus-v1.1-1.5B-Instruct 1.5B F16 3.8 GiB 4,096 ≤ 290 tok/s Fits
granite-4.0-h-1b 1.5B BF16 4.4 GiB 131,072 ≤ 254 tok/s Fits
Llama-3.2-1B-Instruct 1.2B BF16 4.0 GiB 93,184 ≤ 277 tok/s Fits
LFM2.5-1.2B-Base 1.2B BF16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-1.2B-Instruct 1.2B BF16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-1.2B-JP 1.2B F16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-1.2B-JP-202606 1.2B F16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-1.2B-Thinking 1.2B BF16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-VL-1.6B 1.2B BF16 3.7 GiB 128,000 ≤ 311 tok/s Fits
LFM2.5-VL-1.6B-Extract 1.2B F16 3.7 GiB 128,000 ≤ 311 tok/s Fits
MiniCPM5-1B 1.1B Q6_K 2.2 GiB 131,072 ≤ 823 tok/s Fits
MiniCPM5-1B-Base 1.1B Q6_K 2.2 GiB 131,072 ≤ 823 tok/s Fits
MiniCPM5-1B-SFT 1.1B Q6_K 2.2 GiB 131,072 ≤ 823 tok/s Fits
Holo-3.1-0.8B 1.0B Q6_K 2.3 GiB 262,144 ≤ 1,056 tok/s Fits
MiniCPM-V-4.7-1B 1.0B F16 3.2 GiB 262,144 ≤ 473 tok/s Fits
gemma-3-1b-it 1.0B BF16 3.6 GiB 32,768 ≤ 372 tok/s Fits
Qwen3.5-0.8B 752M BF16 3.2 GiB 262,144 ≤ 473 tok/s Fits
Qwen3.5-0.8B-Base 752M Q6_K 2.3 GiB 262,144 ≤ 1,056 tok/s Fits
MiniCPM-V-4.6 752M F16 3.2 GiB 262,144 ≤ 473 tok/s Fits
MiniCPM-V-4.6-Thinking 752M F16 3.2 GiB 262,144 ≤ 473 tok/s Fits
Qwen3-0.6B 752M BF16 3.4 GiB 38,400 ≤ 357 tok/s Fits
HunyuanOCR 539M F16 3.1 GiB 32,768 ≤ 404 tok/s Fits
LFM2.5-350M 354M BF16 2.1 GiB 128,000 ≤ 939 tok/s Fits
LFM2.5-Encoder-350M-Diffusion 354M Q6_K 1.7 GiB 128,000 ≤ 1,940 tok/s Fits
LFM2.5-VL-450M 354M BF16 2.1 GiB 128,000 ≤ 939 tok/s Fits
LFM2.5-VL-450M-Extract 354M F16 2.1 GiB 128,000 ≤ 939 tok/s Fits
granite-4.0-350m 352M BF16 2.2 GiB 32,768 ≤ 809 tok/s Fits
granite-4.0-h-350m 340M BF16 2.1 GiB 32,768 ≤ 1,063 tok/s Fits
functiongemma-270m-it 268M BF16 2.1 GiB 32,768 ≤ 1,335 tok/s Fits
LFM2.5-230M 230M BF16 1.8 GiB 128,000 ≤ 1,357 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
Kimi-Linear-REAP-35B-A3B-Instruct 35.1B (3.1B active) IQ2_XXS 10.7 GiB Tight
Holo4-35B-A3B 34.7B (2.9B active) IQ2_XXS 12.0 GiB Tight
Ising-Calibration-1-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.1 GiB Tight
KAT-Coder-V2.5-Dev 34.7B (2.9B active) IQ2_XXS 11.3 GiB Tight
Qwen3.5-35B-A3B-Base 34.7B (2.9B active) IQ2_XXS 10.9 GiB Tight
Qwen3.6-35B-A3B 34.7B (2.9B active) IQ2_XXS 11.3 GiB Tight
Laguna-XS-2.1 33.4B (2.8B active) IQ2_XXS 11.1 GiB Tight
Cosmos-Reason2-32B 32.8B IQ2_XXS 12.0 GiB Tight
FrogBoss-32B-2510 32.8B IQ2_XXS 12.0 GiB Tight
Nemotron-Terminal-32B 32.8B IQ2_XXS 12.0 GiB Tight
SERA-32B 32.8B IQ2_XXS 12.0 GiB Tight
WebWorld-32B 32.8B IQ2_XXS 12.0 GiB Tight
Olmo-3.1-32B-Instruct-DPO 32.2B IQ2_XXS 11.8 GiB Tight
Olmo-3-1125-32B 32.2B IQ2_XXS 11.8 GiB Tight
Olmo-3-32B-Think-DPO 32.2B IQ2_XXS 11.8 GiB Tight
Olmo-3-32B-Think-SFT 32.2B IQ2_XXS 11.8 GiB Tight
North-Mini-Code-1.0 30.5B (3.3B active) IQ2_M 12.7 GiB Tight
Muse-Glimmer-30B 27.9B IQ3_XXS 12.6 GiB Tight
Fara1.5-27B 26.9B IQ2_M 12.5 GiB Tight
Holo4-27B 26.9B Q2_K 12.7 GiB Tight
Qwen3.8-27B 26.9B Q2_K 12.5 GiB Tight
Qwen3.8-3.6-27B-blend 26.9B Q2_K 12.5 GiB Tight
UI-Mate-27B 26.9B IQ2_M 12.5 GiB Tight
UI-Mate-democua-27B 26.9B Q2_K 12.7 GiB Tight
Trinity-Mini 26.1B (3.1B active) IQ3_XXS 12.1 GiB Tight
Trinity-Mini-Base 26.1B (3.1B active) IQ3_XXS 11.8 GiB Tight
Trinity-Mini-Base-Pre-Anneal 26.1B (3.1B active) IQ3_XXS 11.5 GiB Tight
gemma-4-26B-A4B 25.2B (3.8B active) Q2_K 13.0 GiB Tight
gemma-4-26B-A4B-it 25.2B (3.8B active) IQ2_M 13.1 GiB Tight
Qwen3-Coder-REAP-25B-A3B 24.9B (3.0B active) IQ3_XXS 11.8 GiB Tight
Devstral-Small-2-24B-Instruct-2512 23.6B Q2_K 11.1 GiB Tight
Mistral-Small-3.2-24B-Instruct-2506 23.6B Q2_K 11.1 GiB Tight
GLM-4.7-Flash-REAP-23B-A3B 23.0B (3.6B active) Q2_K 10.2 GiB Tight
EuroLLM-22B-2512 22.6B IQ3_XXS 11.5 GiB Tight
EuroLLM-22B-Instruct-2512 22.6B IQ3_XXS 11.5 GiB Tight
gpt-oss-20b 20.9B (3.6B active) Q2_K 12.6 GiB Tight
DeepSeek-R1-Distill-Qwen-14B 14.8B Q4_K_M 11.3 GiB Tight
Qwen2.5-14B-Instruct 14.8B Q4_K_M 11.3 GiB Tight
ContextPilot-14B 14.8B Q4_K_M 11.3 GiB Tight
JanusCoder-14B 14.8B Q5_K_M 12.4 GiB Tight
Nemotron-Cascade-14B-Thinking 14.8B Q5_K_M 12.4 GiB Tight
NousCoder-14B 14.8B Q5_K_M 12.4 GiB Tight
Qwen3-14B 14.8B Q5_K_M 12.4 GiB Tight
phi-4 14.7B Q4_K_M 11.4 GiB Tight
Apriel-1.6-15b-Thinker 14.4B Q5_K_M 12.5 GiB Tight
Ministral-3-14B-Instruct-2512 13.5B Q5_K_M 11.6 GiB Tight
Ministral-3-14B-Reasoning-2512 13.5B Q5_K_M 11.6 GiB Tight
Mellum2.1-12B-A2.5B-Thinking 12.1B (2.2B active) Q6_K 12.1 GiB Tight
gemma-4-12B-it 11.9B Q6_K 12.7 GiB Tight
gemma-3-12b-it 11.8B Q6_K 13.0 GiB Tight
translategemma-12b-it 11.8B Q6_K 13.0 GiB Tight
Bielik-11B-v3.0-Instruct 11.2B Q6_K 11.8 GiB Tight
gemma-2-9b-it 9.2B Q6_K 12.0 GiB Tight
Ministral-3-8B-Instruct-2512 8.5B Q8_0 10.7 GiB Tight
Ministral-3-8B-Reasoning-2512 8.5B Q8_0 10.7 GiB Tight
ArmorOCR 8.2B Q8_0 10.4 GiB Tight
Qwen3-8B 8.2B Q8_0 10.4 GiB Tight
Bielik-Minitron-7B-v3.0-Instruct 7.5B Q8_0 10.2 GiB Tight
Olmo-3.1-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB Tight
Olmo-3.1-7B-RL-Zero-Math 7.3B Q8_0 12.7 GiB Tight
Olmo-3-7B-Instruct 7.3B Q8_0 12.7 GiB Tight
Olmo-3-7B-Instruct-DPO 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-Instruct-SFT 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-RL-Zero-Code 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-RL-Zero-General 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-RL-Zero-IF 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-RL-Zero-Math 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-RL-Zero-Mix 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-Think 7.3B Q8_0 12.7 GiB Tight
Olmo-3-7B-Think-DPO 7.3B Q6_K 11.0 GiB Tight
Olmo-3-7B-Think-SFT 7.3B Q6_K 11.0 GiB Tight

Models that don’t fit on one NVIDIA GeForce RTX 3080 10GB

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
GLM-4.7-Flash 29.9B (3.6B active) Q2_K 12.8 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Hermes-4.3-36B 36.2B IQ2_XXS 12.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holo2-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-30B-A3B-Instruct-2507 30.5B (3.0B active) Q2_K 13.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-VL-30B-A3B-Instruct 30.5B (3.0B active) Q2_K 13.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
UI-Venus-1.5-30B-A3B 30.5B (3.0B active) Q2_K 13.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
OptiMind-SFT 20.9B (3.6B active) IQ2_M 13.1 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Kimi-Linear-48B-A3B-Instruct 49.1B (3.1B active) IQ2_XXS 13.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
AesCode-32B 32.8B IQ2_XXS 13.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
AI21-Jamba2-Mini 51.6B (11.8B active) IQ2_XXS 13.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gemma-2-27b-it 27.2B IQ2_M 13.8 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
granite-4.1-30b 28.9B Q2_K 13.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
granite-4.2-30b 29.3B Q2_K 13.9 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Kimi-Linear-48B-A3B-Base 49.1B (3.1B active) IQ2_XXS 14.2 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gemma-3-27b-it 27.0B Q2_K 14.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
translategemma-27b-it 27.0B Q2_K 14.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holo-3.1-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holo3-35B-A3B 34.7B (2.9B active) Q2_K 14.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
LFM2-24B-A2B 23.8B (2.3B active) Q4_0 14.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
LFM2.5-24B-A2B 24.0B (2.5B active) Q4_0 14.7 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Olmo-3.1-32B-Instruct 32.2B Q2_K 15.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Olmo-3.1-32B-Think 32.2B Q2_K 15.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Olmo-3-32B-Think 32.2B Q2_K 15.0 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
DeepSeek-R1-Distill-Qwen-32B 32.8B Q2_K 15.2 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen2.5-32B-Instruct 32.8B Q2_K 15.2 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen2.5-Coder-32B-Instruct 32.8B Q2_K 15.2 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-VL-32B-Instruct 32.8B Q2_K 15.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-VL-32B-Thinking 32.8B Q2_K 15.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3.5-27B 26.9B Q3_K_M 15.3 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3.6-27B 26.9B Q3_K_M 15.4 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gemma-4-12B 11.9B Q8_0 15.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Ising-Calibration-1.5-31B-BF16 30.7B IQ2_XXS 16.5 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3.5-35B-A3B 34.7B (2.9B active) Q3_K_M 17.6 GiB 3 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gemma-4-31B 30.7B Q2_K 17.6 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Holotron4-30B-A3B 31.6B (3.2B active) IQ2_M 18.9 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16 31.6B (3.2B active) IQ2_M 18.9 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 31.6B (3.2B active) Q2_K 18.9 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Nemotron-Cascade-2-30B-A3B 31.6B (3.2B active) IQ2_M 19.1 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 31.6B (3.2B active) IQ2_M 19.1 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 31.6B (3.2B active) IQ4_XS 19.1 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
MiniCPM-V-4.7-35B-A3B 34.7B (2.9B active) IQ4_XS 20.0 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-30B-A3B 30.5B (3.0B active) Q4_K_M 20.1 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
gemma-4-31B-it 30.7B Q3_K_M 20.3 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
EXAONE-4.5-33B 32.5B IQ4_XS 20.4 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Llama-3.1-70B-Instruct 70.6B IQ2_XXS 22.3 GiB 4 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-Coder-Next-Base 79.7B (3.6B active) IQ2_XXS 22.3 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Qwen3-32B 32.8B Q4_K_M 22.4 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
QwQ-32B 32.8B Q4_K_M 22.5 GiB 5 identical cards (default even split) are expected to fit. Fewer cards are borderline. Doesn't fit
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 31.6B (3.2B active) Q4_K_M 23.3 GiB 5 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 6 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 6 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 6 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 6 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 6 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 6 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 6 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 7 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 7 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 Borderline with 8 cards. Doesn't fit
Qwen3.5-122B-A10B 122B (9.0B active) IQ2_XXS 35.0 GiB 8 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 7 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 8 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 8 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 8 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 Borderline with 8 cards. Doesn't fit
GLM-4.5-Air 107B (12.8B active) Q2_K 45.6 GiB Borderline with 8 cards. Doesn't fit
GLM-4.6V 107B (12.8B active) Q2_K 45.6 GiB Borderline with 8 cards. Doesn't fit
Step-3.5-Flash 197B (11.5B active) IQ2_XXS 48.9 GiB Borderline with 8 cards. Doesn't fit
Devstral-2-123B-Instruct-2512 125B Q2_K 49.3 GiB Borderline with 8 cards. Doesn't fit
Mistral-Medium-3.5-128B 125B Q2_K 49.3 GiB Borderline with 8 cards. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 121B (12.2B active) IQ2_XXS 49.8 GiB Borderline with 8 cards. Doesn't fit
NVIDIA-Nemotron-3-Super-120B-A12B-BF16 121B (12.2B active) IQ2_XXS 51.0 GiB Borderline with 8 cards. Doesn't fit
gpt-oss-120b 117B (5.1B active) Q2_K 62.8 GiB Borderline with 8 cards. Doesn't fit
MiniMax-M2.7 229B (10.4B active) IQ2_XXS 62.9 GiB Borderline with 8 cards. Doesn't fit
Baichuan-M3-235B 235B (21.6B active) IQ2_XXS 63.2 GiB Borderline with 8 cards. Doesn't fit
Holo2-235B-A22B 235B (21.6B active) IQ2_XXS 63.2 GiB Borderline with 8 cards. Doesn't fit
Qwen3-Nemotron-235B-A22B-GenRM 235B (21.6B active) IQ2_XXS 63.2 GiB Borderline with 8 cards. Doesn't fit
command-a-plus-05-2026-bf16 218B (25.0B active) IQ2_XXS 63.6 GiB Borderline with 8 cards. Doesn't fit
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 121B (12.2B active) Q4_0 71.8 GiB Borderline with 8 cards. Doesn't fit
GLM-4.7-REAP-268B-A32B 269B (32.8B active) IQ2_XXS 73.0 GiB Borderline with 8 cards. Doesn't fit
Step-3.7-Flash 197B (11.5B active) IQ3_XXS 76.1 GiB Borderline with 8 cards. Doesn't fit
Hy3 295B (20.2B active) IQ2_XXS 82.2 GiB Borderline with 8 cards. 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 Borderline with 8 cards. Doesn't fit
MiniMax-M2 229B (10.4B active) Q2_K 84.9 GiB Borderline with 8 cards. Doesn't fit
MiniMax-M2.1 229B (10.4B active) Q2_K 84.9 GiB Borderline with 8 cards. Doesn't fit
MiniMax-M2.5 229B (10.4B active) Q2_K 84.9 GiB Borderline with 8 cards. Doesn't fit
Qwen3-235B-A22B-Instruct-2507 235B (21.6B active) Q2_K 86.7 GiB Borderline with 8 cards. Doesn't fit
Qwen3-VL-235B-A22B-Instruct 235B (21.6B active) Q2_K 86.7 GiB Borderline with 8 cards. Doesn't fit
GLM-5.3-Flash-BF16 313B (16.7B active) IQ2_XXS 92.0 GiB Does not fit even on 8 cards. Doesn't fit
Laguna-S-2.1 118B (8.1B active) Q4_K_M 95.9 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-Base 399B (12.8B active) IQ2_XXS 96.4 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-TrueBase 399B (12.8B active) IQ2_XXS 96.4 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.6-REAP-268B-A32B 269B (32.8B active) Q2_K 100.9 GiB Does not fit even on 8 cards. Doesn't fit
Trinity-Large-Thinking 399B (12.8B active) IQ2_XXS 107.1 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2-Flash 309B (14.8B active) Q2_K 111.6 GiB Does not fit even on 8 cards. Doesn't fit
Intern-S2-397B 396B (16.3B active) IQ2_XXS 114.3 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Flash-MOPD 309B (14.8B active) Q2_K 124.9 GiB Does not fit even on 8 cards. Doesn't fit
MiMo-V2.6-Flash-RL 309B (14.8B active) Q2_K 124.9 GiB Does not fit even on 8 cards. Doesn't fit
K-EXAONE-236B-A23B 237B (22.7B active) IQ4_XS 126.3 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.5 353B (32.9B active) Q2_K 130.7 GiB Does not fit even on 8 cards. Doesn't fit
GLM-4.7 353B (32.9B active) Q2_K 130.7 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-Coder-REAP-363B-A35B 363B (34.5B active) Q2_K 132.7 GiB Does not fit even on 8 cards. Doesn't fit
Qwen3-235B-A22B 235B (21.6B active) Q4_K_M 141.9 GiB Does not fit even on 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

Detailed pages for this GPU