NVIDIA · Volta

Best AI Models for NVIDIA V100 SXM2 32GB

Runs 27–31B and 35B MoE models well; 70B doesn't fit in 32 GB.

32 GB HBM2900 GB/s125 TFLOPS FP16300 WVolta 2018

What LLMs can the V100 SXM2 32GB run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 158 t/s	158 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 188 t/s	188 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 140 t/s	140 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 158 t/s	158 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 188 t/s	188 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 158 t/s	158 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 188 t/s	188 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Math Score	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 140 t/s	140 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.7 t/s	28.7 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 188 t/s	188 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 179 t/s	179 tok/s	Q4_K_M · 3.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 188 t/s	188 tok/s	Q4_K_M · 19.3 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 174 t/s	174 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 163 t/s	163 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 158 t/s	158 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.6 t/s	33.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.7 t/s	28.7 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 158 t/s	158 tok/s	Q4_K_M · 16.5 GB
5	MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 157 t/s	157 tok/s	Q4_K_M · 22.1 GB

See all 346 models on the V100 SXM2 32GB →Best quant that fits · speeds estimated on this card

About the V100 SXM2 32GB

The V100 SXM2 32GB runs 27–31B and 35B MoE models well. Volta generation, released 2018.

GenerationVoltareleased 2018

V100 SXM2 32GB strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 140 tok/s in 22 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 14.1 GB free

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 32 GB here
No FP8 or NVFP4: Volta predates both; use GGUF, AWQ or GPTQ builds

V100 SXM2 32GB tokens per second by model size

Output speed depends on memory bandwidth (900 GB/s). Grey rows need more than 32 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
92.0tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
61.6tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
33.6tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
140tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1176 models on the V100 SXM2 32GB

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA V100 SXM2 32GB — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen2.5 3B Instruct3.1BChatFunctions Q4_K_M·262.3 t/s	Q4_K_M	2.8 GB9%	262.3 t/s	33K	S100, Runs great
Tiny LLM13MChat Q4_K_M·1887.1 t/s	Q4_K_M	0.3 GB1%	1887.1 t/s	1K	S100, Runs great
Gemma 2 9B IT9.2BChat Q4_K_M·95.9 t/s	Q4_K_M	7.3 GB23%	95.9 t/s	8K	S90, Runs great
C4ai Command R7b 12 20248.0BChatFunctions Q4_K_M·110.4 t/s	Q4_K_M	7.9 GB25%	110.4 t/s	—	S93, Runs great
Qwen2.5 1.5B Instruct1.5BChatFunctions Q4_K_M·457.0 t/s	Q4_K_M	1.7 GB5%	457.0 t/s	33K	S100, Runs great
LLaMmlein 1B Prerelease1.1BChat Q4_K_M·579.2 t/s	Q4_K_M	1.0 GB3%	579.2 t/s	2K	S100, Runs great
Param 1 2.9B Instruct2.9BChat BF16·93.0 t/s	BF16	7.1 GB22%	93.0 t/s	8K	S90, Runs great
EuroLLM 1.7B Instruct1.7BChat Q4_K_M·390.0 t/s	Q4_K_M	1.7 GB5%	390.0 t/s	4K	S100, Runs great
FastVLM 7B7.8BChat BF16·36.7 t/s	BF16	16.8 GB52%	36.7 t/s	33K	A73, Runs well
Ministral 3 3B Reasoning 25123.8BReasoningFunctions Q4_K_M·211.2 t/s	Q4_K_M	3.9 GB12%	211.2 t/s	262K	S100, Runs great
Llama 3.2 1B Instruct1.2BChatFunctions Q4_K_M·713.4 t/s	Q4_K_M	2.3 GB7%	713.4 t/s	131K	S100, Runs great
Falcon Mamba Tiny Dev9MChat BF16·29250.0 t/s	BF16	0.4 GB1%	29250.0 t/s	—	S100, Runs great
OlmOCR 2 7B 10258.3BVision Q4_K_M·108.5 t/s	Q4_K_M	6.2 GB19%	108.5 t/s	128K	S93, Runs great
ERNIE 4.5 0.3B Paddle361MChat BF16·562.5 t/s	BF16	1.2 GB4%	562.5 t/s	131K	S100, Runs great
Qwen2.5 1.5B Quantized.w8a81.8BChatFunctions Q4_K_M·409.1 t/s	Q4_K_M	1.8 GB6%	409.1 t/s	33K	S100, Runs great

V100 SXM2 32GB specs, power and PSU

Specs

Architecture: Volta
VRAM: 32 GB HBM2
Memory bandwidth: 900.0 GB/s
FP16 (dense): 125.00 TFLOPS
CUDA cores: 5,120
Tensor cores: 640
Compute capability: 7.0
TDP: 300 W
Released: 2018-03-27

V100 SXM2 32GB FAQ

What is the largest model the V100 SXM2 32GB can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB of 32 GB, and runs at about 140 tok/s.

Can the V100 SXM2 32GB run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 32 GB, and it is the best model that runs well on this card.

Can the V100 SXM2 32GB run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 32 GB on this card.

How many tokens per second does the V100 SXM2 32GB give?

About 33.6 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 4.0 s on a 4K-token prompt.

What power supply does the V100 SXM2 32GB need?

Plan a 600 W PSU (2× the 300 W TDP).

Is 32 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 10 coding models that fit, runs at about 34 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 32 GB or more RTX 5090