NVIDIA · Hopper

Best AI Models for NVIDIA H100 SXM (80 GB)

Runs everything up to 120B MoE well.

80 GB HBM33352 GB/s989 TFLOPS FP16700 WHopper 2022

What LLMs can the H100 SXM run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 107 t/s	107 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 344 t/s	344 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 284 t/s	284 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 107 t/s	107 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 283 t/s	283 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 344 t/s	344 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 284 t/s	284 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 107 t/s	107 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 344 t/s	344 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 284 t/s	284 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 · 125 t/s	125 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 125 t/s	125 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 283 t/s	283 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 107 t/s	107 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 284 t/s	284 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 668 t/s	668 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 399 t/s	399 tok/s	Q4_K_M · 13.1 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 344 t/s	344 tok/s	Q4_K_M · 16.5 GB
4	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 343 t/s	343 tok/s	Q4_K_M · 6.6 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 284 t/s	284 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 107 t/s	107 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 344 t/s	344 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 125 t/s	125 tok/s	Q4_K_M · 17.9 GB

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

About the H100 SXM

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

GenerationHopperreleased 2022

H100 SXM strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 280 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 511 ms

Weaknesses

700 W under load: Plan a 1,400 W PSU; ≈$153 a year at 4 h a day

H100 SXM tokens per second by model size

Output speed depends on memory bandwidth (3352 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
343tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
229tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
125tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
283tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
46.8tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
280tok/s

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

All 1258 models on the H100 SXM

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 SXM — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Ornith 1.5 9B OBLITERATED9.7BChatFunctions Q4_K_M·342.6 t/s	Q4_K_M	6.6 GB8%	342.6 t/s	262K	S100, Runs great
ZDTaichu5.0 9B9.8BVisionFunctions Q4_K_M·337.3 t/s	Q4_K_M	9.2 GB11%	337.3 t/s	—	S100, Runs great
AesCode 32B33.4BVisionCodeFunctions Q4_K_M·105.5 t/s	Q4_K_M	23 GB29%	105.5 t/s	262K	S92, Runs great
LensVLM 9B9.4BVisionFunctions Q4_K_M·350.9 t/s	Q4_K_M	6.5 GB8%	350.9 t/s	262K	S100, Runs great
Gemma 4 31B IT Qat Q4 0 Unquantized31.3BVisionFunctions Q4_K_M·106.9 t/s	Q4_K_M	21.7 GB27%	106.9 t/s	262K	S92, Runs great
Qwopus3.5 9B v39.7BVisionReasoningFunctions Q4_K_M·342.6 t/s	Q4_K_M	6.6 GB8%	342.6 t/s	262K	S100, Runs great
Granite Switch 4.1 8B8.8BChatFunctions Q4_K_M·368.0 t/s	Q4_K_M	8.4 GB10%	368.0 t/s	131K	S100, Runs great
Diffusiongemma 26B A4B IT25.8BVisionFunctions Q4_K_M·342.9 t/s	Q4_K_M	16.5 GB21%	342.9 t/s	262K	S100, Runs great
Cosmos Reason2 2B2.4BVisionChatReasoningFunctions Q4_K_M·1353.3 t/s	Q4_K_M	3.5 GB4%	1353.3 t/s	—	S100, Runs great
Hy MT2 30B A3B30.1BTranslationFunctions Q4_K_M·276.9 t/s	Q4_K_M	19.1 GB24%	276.9 t/s	262K	S100, Runs great
Ring Flash 2.0102.9BChat Q4_K_M·288.5 t/s	Q4_K_M	63.1 GB79%	288.5 t/s	33K	S100, Runs great
Intern Decision 4B4.5BVisionFunctions Q4_K_M·683.0 t/s	Q4_K_M	3.4 GB4%	683.0 t/s	262K	S100, Runs great
Ornith 1.5 9B9.7BChatFunctions Q4_K_M·342.6 t/s	Q4_K_M	6.6 GB8%	342.6 t/s	262K	S100, Runs great
MinerU2.5 Pro 2604 1.2B1.2BVision Q4_K_M·2136.1 t/s	Q4_K_M	1.1 GB1%	2136.1 t/s	8K	S100, Runs great
Youtu Parsing Omni5.3BVision BF16·194.9 t/s	BF16	12.7 GB16%	194.9 t/s	1049K	S99, Runs great

Rent NVIDIA H100 SXM in the cloud

Hourly rate on demand for one H100 SXM.

RunPod$5+ bonus creditLowest price
from$2.69/hr
Deploy
Vast.aiMarketplace
from$3.58/hr
Deploy

Cost per million tokens

Output-token cost on an H100 SXM rented at $2.69/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.

Model	Quant	Speed	Per 1M output
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16	Q4_K_M	284 tok/s	$2.63$0.015 input
GLM 4.7 Flash	Q4_K_M	255 tok/s	$2.93$0.015 input
Qwen3.8 27B	Q4_K_M	125 tok/s	$5.97$0.093 input
Muse Glimmer 30B	Q4_K_M	119 tok/s	$6.29$0.10 input
Gemma 4 31B IT	Q4_K_M	107 tok/s	$6.99$0.10 input

H100 SXM specs, power and PSU

Specs

Architecture: Hopper
VRAM: 80 GB HBM3
Memory bandwidth: 3352.0 GB/s
FP16 (dense): 989.40 TFLOPS
CUDA cores: 16,896
Tensor cores: 528
Compute capability: 9.0
TDP: 700 W
Released: 2022-09-01

H100 SXM FAQ

What is the largest model the H100 SXM 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 29.9 tok/s.

Can the H100 SXM 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 SXM give?

About 125 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 0.5 s on a 4K-token prompt.

What power supply does the H100 SXM need?

Plan a 1400 W PSU (2× the 700 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 125 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 RTX 5090