NVIDIA · Hopper (Grace Hopper)

Best AI Models for NVIDIA GH200 Grace Hopper Superchip (144 GB)

Runs everything up to 120B MoE well.

144 GB HBM3e4900 GB/s990 TFLOPS FP161000 WHopper (Grace Hopper) 2024

Grace Hopper superchip: 144 GB HBM3e GPU pool plus a large NVLink-coherent LPDDR5X extension. Server/cloud part, listed for comparison.

What LLMs can the GH200 Grace Hopper Superchip run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q3_K_M · 132.8 GB · 389 t/s	389 tok/s	Q3_K_M · 132.8 GB
3	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 156 t/s	156 tok/s	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 156 t/s	156 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 322 t/s	322 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 398 t/s	398 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q3_K_M · 132.8 GB · 389 t/s	389 tok/s	Q3_K_M · 132.8 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 156 t/s	156 tok/s	Q4_K_M · 21.7 GB
4	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q3_K_M · 132.8 GB · 389 t/s	389 tok/s	Q3_K_M · 132.8 GB
3	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
4	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 322 t/s	322 tok/s	Q4_K_M · 22.0 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 156 t/s	156 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 398 t/s	398 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 977 t/s	977 tok/s	Q4_K_M · 3.4 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 501 t/s	501 tok/s	Q4_K_M · 6.6 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 469 t/s	469 tok/s	Q4_K_M · 13.1 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 398 t/s	398 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 302 t/s	302 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
2	Inkling SmallThinking Machines Q3_K_M · 132.8 GB · 389 t/s	389 tok/s	Q3_K_M · 132.8 GB
3	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 183 t/s	183 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 156 t/s	156 tok/s	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Super VL 120B A12B BF16NVIDIA Q4_K_M · 87.7 GB · 195 t/s	195 tok/s	Q4_K_M · 87.7 GB

See all 405 models on the GH200 Grace Hopper Superchip →Best quant that fits · speeds estimated on this card

About the GH200 Grace Hopper Superchip

The GH200 Grace Hopper Superchip runs everything up to 120B MoE well. Hopper (Grace Hopper) generation, released 2024.

GenerationHopper (Grace Hopper)released 2024

GH200 Grace Hopper Superchip strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 326 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 92.7 GB free
Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 511 ms

Weaknesses

1000 W under load: Plan a 2,000 W PSU; ≈$219 a year at 4 h a day

GH200 Grace Hopper Superchip tokens per second by model size

Output speed depends on memory bandwidth (4900 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
501tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
335tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
183tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
322tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
68.4tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
326tok/s

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

All 1296 models on the GH200 Grace Hopper Superchip

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 GH200 Grace Hopper Superchip — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Tiny Random Gemma2ForCausalLM8MChat Q4_K_M·10274.2 t/s	Q4_K_M	0.3 GB0%	10274.2 t/s	8K	S100, Runs great
LFM2.5 350M354MChatFunctions Q4_K_M·5491.4 t/s	Q4_K_M	0.8 GB1%	5491.4 t/s	128K	S100, Runs great
Aria25.3BVision Q4_K_M·408.5 t/s	Q4_K_M	20.2 GB14%	408.5 t/s	66K	S100, Runs great
Param 1 5B5BChat BF16·305.4 t/s	BF16	10.6 GB7%	305.4 t/s	4K	S100, Runs great
Qwen3 Tiny Random10MChatFunctions Q4_K_M·10274.2 t/s	Q4_K_M	0.3 GB0%	10274.2 t/s	41K	S100, Runs great
Dream V0 Instruct 7B7.6BChatFunctions Q4_K_M·638.3 t/s	Q4_K_M	5.8 GB4%	638.3 t/s	131K	S100, Runs great
INTELLECT 1 Instruct10.2BChat Q4_K_M·469.8 t/s	Q4_K_M	7.8 GB5%	469.8 t/s	8K	S100, Runs great
Qwen3 30B A3B.w8a830.6BChatFunctions Q4_K_M·304.0 t/s	Q4_K_M	19.4 GB13%	304.0 t/s	41K	S100, Runs great
Nemotron 3 Nano Omni 30B A3B Reasoning BF1633.0BReasoning Q4_K_M·271.8 t/s	Q4_K_M	25.6 GB18%	271.8 t/s	—	S100, Runs great
Llama XLAM 2 8B Fc R8.0BChatFunctions Q4_K_M·590.9 t/s	Q4_K_M	7.3 GB5%	590.9 t/s	131K	S100, Runs great
Darkidol Ballad 27B26.9BChatRoleplay BF16·58.4 t/s	BF16	55.0 GB38%	58.4 t/s	262K	A83, Runs well
Qwen Marketing8.2BChatReasoning BF16·176.7 t/s	BF16	20.6 GB14%	176.7 t/s	—	S99, Runs great
TildeOpen 30B30.7BChat Q4_K_M·165.8 t/s	Q4_K_M	22.7 GB16%	165.8 t/s	66K	S98, Runs great
MiMo 7B RL7.8BChatFunctions Q4_K_M·600.9 t/s	Q4_K_M	7.4 GB5%	600.9 t/s	33K	S100, Runs great
Huihui Qwen3 Coder 30B A3B Instruct Abliterated30.5BChatCodeFunctions Q4_K_M·304.4 t/s	Q4_K_M	19.4 GB13%	304.4 t/s	262K	S100, Runs great

GH200 Grace Hopper Superchip specs, power and PSU

Specs

Architecture: Hopper (Grace Hopper)
VRAM: 144 GB HBM3e
Memory bandwidth: 4900.0 GB/s
FP16 (dense): 989.50 TFLOPS
CUDA cores: 16,896
Tensor cores: 528
Compute capability: 9.0
TDP: 1000 W
Released: 2024-01-01

GH200 Grace Hopper Superchip FAQ

What is the largest model the GH200 Grace Hopper Superchip can run?

Qwen3 235B A22B Thinking 2507 (235.1B) is the largest at 4-bit or better: at Q4_K_M it uses 142.9 GB of 144 GB, and runs at about 107 tok/s. At 3-bit, a bigger model fits too: DeepSeek V4 Flash 0731 (304.2B) at IQ3_M, 137.4 GB.

Can the GH200 Grace Hopper Superchip run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 144 GB, and it is the best model that runs well on this card.

How many tokens per second does the GH200 Grace Hopper Superchip give?

About 183 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 GH200 Grace Hopper Superchip need?

Plan a 2000 W PSU (2× the 1000 W TDP).

Is 144 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 14 coding models that fit, runs at about 183 tok/s.

Best coding LLMs 48 GB VRAM GPUs with 144 GB or more RTX 5090 RTX 4090