Open-weight models that run on NVIDIA H100 SXM

Memory 80 GB
Bandwidth 3350 GB/s
Usable 72.0 GB

Specs: Memory · H100 GPU | NVIDIA · Bandwidth · H100 GPU | NVIDIA

Search Precision Context Concurrent requests Minimum speed Architecture Type Maker Sort

Fit	Model	Parameters / active	Precision	Memory	Est. speed	Longest context	Runs as
Runs well	Ming-3.0-audio-flash Ant Group	128.2B / 6.5B	Q4_0	70.9 / 72.0 GB	413–620 tok/s	32K	One GPU
Runs well	Ling-3.0-flash Ant Group	127.5B / 5.1B	Q4_0	70.5 / 72.0 GB	513–769 tok/s	40K	One GPU
Runs well	Qwen3.5-122B-A10B Alibaba Qwen	125.1B / 10B	Q4_0	69.0 / 72.0 GB	287–431 tok/s	136K	One GPU
Runs well	Ling-3.0-flash-VL Ant Group	124.8B / 5.5B	Q4_0	69.0 / 72.0 GB	480–720 tok/s	72K	One GPU
Runs well	gpt-oss-120b OpenAI	116.8B / 5.1B	MXFP4 (native)maker’s file	64.1 / 72.0 GB	531–796 tok/s	128K	One GPU
Runs well	GLM-4.5-Air Zhipu AI	110.5B	Q4_0	62.2 / 72.0 GB	151–226 tok/s	63K	One GPU
Runs well	GLM-4.5V Zhipu AI	107.7B / 12B	Q4_0	60.7 / 72.0 GB	202–303 tok/s	63K	One GPU
Runs well	GLM-4.6V Zhipu AI	107.7B	Q4_0	60.7 / 72.0 GB	175–262 tok/s	71K	One GPU
Runs well	Ling-2.6-flash Ant Group	107.5B / 7.4B	Q4_K_M	64.1 / 72.0 GB	349–524 tok/s	128K	One GPU
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	Q6_Kmaker’s file	64.3 / 72.0 GB	640–959 tok/s	256K	One GPU
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	Q6_Kmaker’s file	64.3 / 72.0 GB	640–959 tok/s	256K	One GPU
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	Q6_Kmaker’s file	64.3 / 72.0 GB	628–941 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	Q6_K	61.5 / 72.0 GB	27–40 tok/s	42K	One GPU
Runs well	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	Q6_K	61.5 / 72.0 GB	27–40 tok/s	32K	One GPU
Runs well	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	Q6_Kmaker’s file	61.0 / 72.0 GB	27–40 tok/s	32K	One GPU
Runs well	Qianfan-VL-70B Baidu	71.8B	Q6_K	60.2 / 72.0 GB	27–41 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	Q6_K	59.2 / 72.0 GB	28–41 tok/s	49K	One GPU
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 72.0 GB	499–749 tok/s	256K	One GPU
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 72.0 GB	499–749 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	Q8_0	36.8 / 72.0 GB	44–67 tok/s	125K	One GPU
Runs well	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	Q8_0maker’s file	36.0 / 72.0 GB	45–68 tok/s	128K	One GPU
Runs well	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	Q8_0maker’s file	36.0 / 72.0 GB	45–68 tok/s	128K	One GPU
Runs well	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	Q8_0maker’s file	36.1 / 72.0 GB	45–68 tok/s	32K	One GPU
Runs well	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	INT8 (GPTQ)maker’s file	36.3 / 72.0 GB	45–68 tok/s	32K	One GPU
Runs well	QwQ-32B Alibaba Qwen	32.8B	Q8_0maker’s file	36.1 / 72.0 GB	45–68 tok/s	40K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	Q8_0	36.0 / 72.0 GB	45–68 tok/s	32K	One GPU
Runs well	Qwen3-32B Alibaba Qwen	32.8B	Q8_0maker’s file	36.0 / 72.0 GB	45–68 tok/s	128K	One GPU
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	BF16 (native)maker’s file	62.8 / 72.0 GB	169–254 tok/s	64K	One GPU
Runs well	Gemma 4 31B IT Google	31.3B	BF16 (native)maker’s file	63.2 / 72.0 GB	26–39 tok/s	64K	One GPU
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	BF16 (native)maker’s file	61.5 / 72.0 GB	155–233 tok/s	195K	One GPU
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 72.0 GB	195–293 tok/s	120K	One GPU
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 72.0 GB	195–293 tok/s	120K	One GPU
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 72.0 GB	226–339 tok/s	256K	One GPU
Runs well	Qwen3-30B-A3B-Thinking-2507 Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 72.0 GB	226–339 tok/s	256K	One GPU
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 72.0 GB	226–339 tok/s	128K	One GPU
Runs well	Qwen3-Coder-30B-A3B-Instruct Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 72.0 GB	226–339 tok/s	131K	One GPU
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	BF16 (native)maker’s file	59.6 / 72.0 GB	246–369 tok/s	63K	One GPU
Runs well	Granite Switch 4.1 30B IBM	30B	BF16 (native)maker’s file	60.7 / 72.0 GB	27–40 tok/s	52K	One GPU
Runs well	Qwen3.5-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 72.0 GB	30–45 tok/s	256K	One GPU
Runs well	Qwen3.6-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 72.0 GB	30–45 tok/s	256K	One GPU
Runs well	Qwen3.8-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 72.0 GB	30–45 tok/s	256K	One GPU
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	BF16 (native)maker’s file	51.0 / 72.0 GB	206–308 tok/s	250K	One GPU
Runs well	Magistral Small 1.2 Mistral AI	24B	Q8_0maker’s file	25.8 / 72.0 GB	63–95 tok/s	125K	One GPU
Runs well	Devstral Small 1.0 Mistral AI	23.6B	Q8_0	25.7 / 72.0 GB	63–95 tok/s	125K	One GPU
Runs well	Devstral Small 1.1 Mistral AI	23.6B	Q8_0	25.7 / 72.0 GB	63–95 tok/s	125K	One GPU
Runs well	Magistral Small 1.0 Mistral AI	23.6B	Q8_0	25.7 / 72.0 GB	63–95 tok/s	39K	One GPU
Runs well	Magistral Small 1.1 Mistral AI	23.6B	Q8_0maker’s file	25.8 / 72.0 GB	63–95 tok/s	39K	One GPU
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	BF16 (native)maker’s file	43.1 / 72.0 GB	259–388 tok/s	128K	One GPU
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 72.0 GB	651–976 tok/s	128K	One GPU
Runs well	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 72.0 GB	54–81 tok/s	230K	One GPU
Runs well	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 72.0 GB	54–81 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	BF16 (native)maker’s file	30.4 / 72.0 GB	54–81 tok/s	32K	One GPU
Runs well	Qwen3-14B Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.1 / 72.0 GB	54–81 tok/s	128K	One GPU
Runs well	Gemma 3 12B IT Google	12.2B	BF16 (native)maker’s file	26.6 / 72.0 GB	61–92 tok/s	128K	One GPU
Runs well	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	BF16 (native)maker’s file	22.3 / 72.0 GB	73–110 tok/s	32K	One GPU
Runs well	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 72.0 GB	80–120 tok/s	125K	One GPU
Runs well	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 72.0 GB	86–128 tok/s	256K	One GPU
Runs well	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 72.0 GB	90–134 tok/s	32K	One GPU
Runs well	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 72.0 GB	88–132 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 72.0 GB	89–134 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 72.0 GB	89–134 tok/s	128K	One GPU
Runs well	pplx-embed-v2-context-9b Perplexity	8.4B	FP32 (native)maker’s file	33.1 / 72.0 GB	49–74 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 72.0 GB	98–147 tok/s	125K	One GPU
Runs well	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 72.0 GB	95–143 tok/s	128K	One GPU
Runs well	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 72.0 GB	98–147 tok/s	125K	One GPU
Runs well	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 72.0 GB	104–156 tok/s	125K	One GPU
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 72.0 GB	593–889 tok/s	128K	One GPU
Runs well	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 72.0 GB	107–160 tok/s	977K	One GPU
Runs well	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 72.0 GB	107–160 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 72.0 GB	107–160 tok/s	32K	One GPU
Runs well	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 72.0 GB	108–162 tok/s	32K	One GPU
Runs well	Gemma 4 E2B Google	5.1B	BF16 (native)maker’s file	10.1 / 72.0 GB	162–243 tok/s	125K	One GPU
Runs well	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 72.0 GB	154–231 tok/s	256K	One GPU
Runs well	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 72.0 GB	157–235 tok/s	31K	One GPU
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	BF16 (native)maker’s file	9.4 / 72.0 GB	175–262 tok/s	256K	One GPU
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	BF16 (native)maker’s file	9.9 / 72.0 GB	166–249 tok/s	250K	One GPU
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 72.0 GB	181–272 tok/s	256K	One GPU
Runs well	Qwen3-4B Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 72.0 GB	181–272 tok/s	128K	One GPU
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 72.0 GB	601–902 tok/s	8K	One GPU
Runs well	Granite-4.0-H-Micro IBM	3.2B	BF16 (native)maker’s file	6.5 / 72.0 GB	260–390 tok/s	128K	One GPU
Runs well	Qwen3-1.7B Alibaba Qwen	2B	BF16 (native)maker’s file	5.2 / 72.0 GB	335–502 tok/s	40K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	BF16 (native)maker’s file	4.0 / 72.0 GB	442–663 tok/s	125K	One GPU
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 72.0 GB	525–788 tok/s	128K	One GPU
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 72.0 GB	686–1029 tok/s	40K	One GPU
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 72.0 GB	1062–1593 tok/s	256K	One GPU
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 72.0 GB	786–1179 tok/s	32K	One GPU
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 72.0 GB	544–817 tok/s	8K	One GPU
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 72.0 GB	544–817 tok/s	8K	One GPU
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 72.0 GB	1204–1806 tok/s	512	One GPU
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 72.0 GB	1481–2221 tok/s	514	One GPU
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 72.0 GB	3667–5500 tok/s	512	One GPU
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 72.0 GB	11721–17582 tok/s	512	One GPU
Needs system memory	Qwen3-VL-235B-A22B-Instruct Alibaba Qwen	235.7B	IQ4_XS	123.9 GB, 52.1 in system memory	8–12 tok/s	—	42/94 layers in system memory
Needs system memory	Qwen3-VL-235B-A22B-Thinking Alibaba Qwen	235.7B	IQ4_XS	123.9 GB, 52.1 in system memory	8–12 tok/s	—	42/94 layers in system memory
Needs system memory	Qwen3-235B-A22B-Instruct-2507 Alibaba Qwen	235.1B / 22B	IQ4_XS	123.6 GB, 52.0 in system memory	8–12 tok/s	—	42/94 layers in system memory
Needs system memory	Qwen3-235B-A22B-Thinking-2507 Alibaba Qwen	235.1B / 22B	IQ4_XS	123.6 GB, 52.0 in system memory	8–12 tok/s	—	42/94 layers in system memory
Needs system memory	Qwen3-235B-A22B Alibaba Qwen	235.1B / 22B	INT4 (AWQ / GPTQ)maker’s file	123.3 GB, 51.8 in system memory	8–12 tok/s	—	42/94 layers in system memory
Needs system memory	MiniMax-M2.1 MiniMax	228.7B	Q4_0	127.7 GB, 56.0 in system memory	15–22 tok/s	—	29/62 layers in system memory
Needs system memory	MiniMax-M2.5 MiniMax	228.7B	Q4_0	127.7 GB, 56.0 in system memory	15–22 tok/s	—	29/62 layers in system memory
Needs system memory	MiniMax-M2.7 MiniMax	228.7B	Q4_0	127.7 GB, 56.0 in system memory	15–22 tok/s	—	29/62 layers in system memory
Needs system memory	MiniMax-M2 MiniMax	228.7B / 10B	Q4_0	127.7 GB, 56.0 in system memory	17–25 tok/s	—	29/62 layers in system memory
Needs system memory	MiniMax-M3.1-Flash MiniMax	220.5B / 23B	IQ4_XS	115.5 GB, 43.6 in system memory	9–13 tok/s	—	24/60 layers in system memory
Needs system memory	Step 3.7 Flash StepFun	201.4B	Q4_K_M	121.0 GB, 50.6 in system memory	50–76 tok/s	—	20/45 layers in system memory
Needs system memory	Step 3.5 Flash StepFun	199.4B / 11B	Q4_K_M	119.9 GB, 50.1 in system memory	15–22 tok/s	—	20/45 layers in system memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated