NVIDIA · Hopper

Best AI Models for NVIDIA H100 PCIe (80 GB)

Runs everything up to 120B MoE well.

80 GB HBM2e2039 GB/s757 TFLOPS FP16350 WHopper 2022

What LLMs can the H100 PCIe run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 228 t/s	228 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 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 · 76.1 t/s	76.1 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 228 t/s	228 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 407 t/s	407 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 305 t/s	305 tok/s	Q4_K_M · 13.1 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB
5	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 239 t/s	239 tok/s	Q4_K_M · 19.4 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB

See all 383 models on the H100 PCIe →Best quant that fits · speeds estimated on this card

About the H100 PCIe

The H100 PCIe runs everything up to 120B MoE well. Hopper generation, released 2022.

GenerationHopperreleased 2022

H100 PCIe strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 218 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 28.7 GB free
Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 669 ms

H100 PCIe tokens per second by model size

Output speed depends on memory bandwidth (2039 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
208tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
140tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
76.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
228tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
28.5tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
218tok/s

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

All 1258 models on the H100 PCIe

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 H100 PCIe — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3 4B Instruct 25074.0BChatFunctions Q4_K_M·457.0 t/s	Q4_K_M	4.2 GB5%	457.0 t/s	262K	S100, Runs great
LightOnOCR 3 0.8B853MVisionFunctions Q4_K_M·1541.1 t/s	Q4_K_M	0.9 GB1%	1541.1 t/s	262K	S100, Runs great
Turkish Gemma 4B T1 Scout4.3BChatFunctionsReasoning Q4_K_M·409.1 t/s	Q4_K_M	3.6 GB5%	409.1 t/s	131K	S100, Runs great
XiaoHong V18.2BChat Q4_K_M·240.1 t/s	Q4_K_M	7.6 GB10%	240.1 t/s	41K	S100, Runs great
Huihui Qwen3 8B Abliterated v28.2BChatFunctions Q4_K_M·240.1 t/s	Q4_K_M	7.6 GB10%	240.1 t/s	41K	S100, Runs great
Huihui GPT OSS 20B BF16 Abliterated20.9BChatFunctions Q4_K_M·305.4 t/s	Q4_K_M	13.1 GB16%	305.4 t/s	131K	S100, Runs great
Gemma4 E4B MiniFantasy V18.0BChatRoleplay BF16·80.3 t/s	BF16	16.8 GB21%	80.3 t/s	131K	S88, Runs great
GrepSeek Qwen3.5 9B GRPO9.4BChatFunctions BF16·68.4 t/s	BF16	19.7 GB25%	68.4 t/s	262K	S85, Runs great
Tiny Random LlamaForCausalLM1MChat Q4_K_M·4417.8 t/s	Q4_K_M	0.3 GB0%	4417.8 t/s	8K	S100, Runs great
Llamatron 8B V18.0BChat Q4_K_M·245.9 t/s	Q4_K_M	7.3 GB9%	245.9 t/s	131K	S100, Runs great
Recursive Language Model 198M198MChat BF16·3012.2 t/s	BF16	0.4 GB1%	3012.2 t/s	1K	S100, Runs great
TeleOCR1.4BVision Q4_K_M·1043.6 t/s	Q4_K_M	2.1 GB3%	1043.6 t/s	128K	S100, Runs great
Kimi Dev 72B72.7BChatCodeFunctions Q4_K_M·29.7 t/s	Q4_K_M	49.3 GB62%	29.7 t/s	131K	A71, Runs well
Hermes 4.3 36B36.2BChatReasoningRoleplay Q4_K_M·59.5 t/s	Q4_K_M	24.1 GB30%	59.5 t/s	524K	A84, Runs well
Qehwa Pashto Llm7.6BChat Q4_K_M·265.6 t/s	Q4_K_M	5.8 GB7%	265.6 t/s	131K	S100, Runs great

H100 PCIe specs, power and PSU

Specs

Architecture: Hopper
VRAM: 80 GB HBM2e
Memory bandwidth: 2039.0 GB/s
FP16 (dense): 756.50 TFLOPS
CUDA cores: 14,592
Tensor cores: 456
Compute capability: 9.0
TDP: 350 W
Released: 2022-09-01

H100 PCIe FAQ

What is the largest model the H100 PCIe can run?

Mistral Medium 3.5 128B (127.7B) is the largest at 4-bit or better: at Q4_K_S it uses 78.0 GB of 80 GB, and runs at about 18.2 tok/s.

Can the H100 PCIe run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 80 GB, and it is the best model that runs well on this card.

How many tokens per second does the H100 PCIe give?

About 76.1 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 0.7 s on a 4K-token prompt.

What power supply does the H100 PCIe need?

Plan a 700 W PSU (2× the 350 W TDP).

Is 80 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 12 coding models that fit, runs at about 76 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 48 GB VRAM GPUs with 80 GB or more