Open-weight models that run on NVIDIA H200 SXM

Memory 141 GB
Bandwidth 4800 GB/s
Usable 126.9 GB

Specs: Memory · H200 GPU | NVIDIA · Bandwidth · H200 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	Qwen3-VL-235B-A22B-Instruct Alibaba Qwen	235.7B	IQ4_XS	123.9 / 126.9 GB	176–263 tok/s	24K	One GPU
Runs well	Qwen3-VL-235B-A22B-Thinking Alibaba Qwen	235.7B	IQ4_XS	123.9 / 126.9 GB	176–263 tok/s	24K	One GPU
Runs well	Qwen3-235B-A22B-Instruct-2507 Alibaba Qwen	235.1B / 22B	IQ4_XS	123.6 / 126.9 GB	181–271 tok/s	26K	One GPU
Runs well	Qwen3-235B-A22B-Thinking-2507 Alibaba Qwen	235.1B / 22B	IQ4_XS	123.6 / 126.9 GB	181–271 tok/s	26K	One GPU
Runs well	Qwen3-235B-A22B Alibaba Qwen	235.1B / 22B	INT4 (AWQ / GPTQ)maker’s file	123.3 / 126.9 GB	181–272 tok/s	28K	One GPU
Runs well	MiniMax-M2.1 MiniMax	228.7B	IQ4_XS	120.7 / 126.9 GB	302–453 tok/s	33K	One GPU
Runs well	MiniMax-M2.5 MiniMax	228.7B	IQ4_XS	120.7 / 126.9 GB	302–453 tok/s	33K	One GPU
Runs well	MiniMax-M2.7 MiniMax	228.7B	IQ4_XS	120.7 / 126.9 GB	302–453 tok/s	33K	One GPU
Runs well	MiniMax-M2 MiniMax	228.7B / 10B	IQ4_XS	120.7 / 126.9 GB	325–487 tok/s	33K	One GPU
Runs well	MiniMax-M3.1-Flash MiniMax	220.5B / 23B	Q4_0	122.2 / 126.9 GB	172–258 tok/s	48K	One GPU
Runs well	Step 3.7 Flash StepFun	201.4B	Q4_0	112.2 / 126.9 GB	727–1091 tok/s	91K	One GPU
Runs well	Step 3.5 Flash StepFun	199.4B / 11B	Q4_0	111.1 / 126.9 GB	312–468 tok/s	98K	One GPU
Runs well	Ming-3.0-audio-flash Ant Group	128.2B / 6.5B	Q6_K	103.3 / 126.9 GB	419–628 tok/s	128K	One GPU
Runs well	Ling-3.0-flash Ant Group	127.5B / 5.1B	Q6_Kmaker’s file	102.8 / 126.9 GB	523–785 tok/s	250K	One GPU
Runs well	Qwen3.5-122B-A10B Alibaba Qwen	125.1B / 10B	Q6_K	100.6 / 126.9 GB	285–428 tok/s	256K	One GPU
Runs well	Ling-3.0-flash-VL Ant Group	124.8B / 5.5B	Q6_K	100.6 / 126.9 GB	488–733 tok/s	128K	One GPU
Runs well	gpt-oss-120b OpenAI	116.8B / 5.1B	MXFP4 (native)maker’s file	64.1 / 126.9 GB	761–1141 tok/s	128K	One GPU
Runs well	GLM-4.5-Air Zhipu AI	110.5B	FP8maker’s file	111.5 / 126.9 GB	127–190 tok/s	94K	One GPU
Runs well	GLM-4.5V Zhipu AI	107.7B / 12B	Q8_0	113.3 / 126.9 GB	168–252 tok/s	63K	One GPU
Runs well	GLM-4.6V Zhipu AI	107.7B	Q8_0	113.3 / 126.9 GB	144–215 tok/s	83K	One GPU
Runs well	Ling-2.6-flash Ant Group	107.5B / 7.4B	Q8_0	112.0 / 126.9 GB	294–441 tok/s	128K	One GPU
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 126.9 GB	721–1081 tok/s	256K	One GPU
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 126.9 GB	721–1081 tok/s	256K	One GPU
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	Q8_0maker’s file	83.1 / 126.9 GB	707–1060 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	Q8_0	78.8 / 126.9 GB	30–45 tok/s	125K	One GPU
Runs well	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	Q8_0	78.8 / 126.9 GB	30–45 tok/s	32K	One GPU
Runs well	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	Q8_0maker’s file	78.3 / 126.9 GB	30–45 tok/s	32K	One GPU
Runs well	Qianfan-VL-70B Baidu	71.8B	Q8_0	77.1 / 126.9 GB	30–46 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	Q8_0	75.8 / 126.9 GB	31–46 tok/s	125K	One GPU
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	BF16 (native)maker’s file	70.5 / 126.9 GB	389–584 tok/s	256K	One GPU
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	BF16 (native)maker’s file	70.5 / 126.9 GB	389–584 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	BF16 (native)maker’s file	68.8 / 126.9 GB	34–51 tok/s	125K	One GPU
Runs well	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	BF16 (native)maker’s file	67.2 / 126.9 GB	35–52 tok/s	128K	One GPU
Runs well	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	BF16 (native)maker’s file	67.2 / 126.9 GB	35–52 tok/s	128K	One GPU
Runs well	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 126.9 GB	35–53 tok/s	32K	One GPU
Runs well	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 126.9 GB	35–53 tok/s	32K	One GPU
Runs well	QwQ-32B Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 126.9 GB	35–53 tok/s	40K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	BF16 (native)maker’s file	66.1 / 126.9 GB	35–53 tok/s	32K	One GPU
Runs well	Qwen3-32B Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 126.9 GB	35–53 tok/s	128K	One GPU
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	BF16 (native)maker’s file	62.8 / 126.9 GB	243–364 tok/s	64K	One GPU
Runs well	Gemma 4 31B IT Google	31.3B	BF16 (native)maker’s file	63.2 / 126.9 GB	37–56 tok/s	250K	One GPU
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	BF16 (native)maker’s file	61.5 / 126.9 GB	222–334 tok/s	195K	One GPU
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 126.9 GB	279–419 tok/s	128K	One GPU
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 126.9 GB	279–419 tok/s	128K	One GPU
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 126.9 GB	324–486 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 / 126.9 GB	324–486 tok/s	256K	One GPU
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 126.9 GB	324–486 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 / 126.9 GB	324–486 tok/s	256K	One GPU
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	BF16 (native)maker’s file	59.6 / 126.9 GB	353–529 tok/s	63K	One GPU
Runs well	Granite Switch 4.1 30B IBM	30B	BF16 (native)maker’s file	60.7 / 126.9 GB	39–58 tok/s	128K	One GPU
Runs well	Qwen3.5-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 126.9 GB	43–64 tok/s	256K	One GPU
Runs well	Qwen3.6-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 126.9 GB	43–64 tok/s	256K	One GPU
Runs well	Qwen3.8-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 126.9 GB	43–64 tok/s	256K	One GPU
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	BF16 (native)maker’s file	51.0 / 126.9 GB	295–442 tok/s	250K	One GPU
Runs well	Magistral Small 1.2 Mistral AI	24B	BF16 (native)maker’s file	95.2 / 126.9 GB	25–37 tok/s	125K	One GPU
Runs well	Devstral Small 1.0 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 126.9 GB	25–38 tok/s	125K	One GPU
Runs well	Devstral Small 1.1 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 126.9 GB	25–38 tok/s	125K	One GPU
Runs well	Magistral Small 1.0 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 126.9 GB	25–38 tok/s	39K	One GPU
Runs well	Magistral Small 1.1 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 126.9 GB	25–38 tok/s	39K	One GPU
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	BF16 (native)maker’s file	43.1 / 126.9 GB	371–556 tok/s	128K	One GPU
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 126.9 GB	933–1399 tok/s	128K	One GPU
Runs well	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 126.9 GB	77–116 tok/s	523K	One GPU
Runs well	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 126.9 GB	77–116 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	BF16 (native)maker’s file	30.4 / 126.9 GB	77–116 tok/s	32K	One GPU
Runs well	Qwen3-14B Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.1 / 126.9 GB	78–117 tok/s	128K	One GPU
Runs well	Gemma 3 12B IT Google	12.2B	BF16 (native)maker’s file	26.6 / 126.9 GB	88–131 tok/s	128K	One GPU
Runs well	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	BF16 (native)maker’s file	22.3 / 126.9 GB	105–158 tok/s	32K	One GPU
Runs well	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 126.9 GB	115–172 tok/s	125K	One GPU
Runs well	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 126.9 GB	123–184 tok/s	256K	One GPU
Runs well	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 126.9 GB	128–193 tok/s	32K	One GPU
Runs well	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 126.9 GB	127–190 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 126.9 GB	128–192 tok/s	128K	One GPU
Runs well	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 126.9 GB	128–192 tok/s	128K	One GPU
Runs well	pplx-embed-v2-context-9b Perplexity	8.4B	FP32 (native)maker’s file	33.1 / 126.9 GB	71–106 tok/s	256K	One GPU
Runs well	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 126.9 GB	141–211 tok/s	125K	One GPU
Runs well	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 126.9 GB	136–205 tok/s	128K	One GPU
Runs well	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 126.9 GB	140–210 tok/s	125K	One GPU
Runs well	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 126.9 GB	149–223 tok/s	125K	One GPU
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 126.9 GB	849–1274 tok/s	128K	One GPU
Runs well	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 126.9 GB	153–229 tok/s	977K	One GPU
Runs well	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 126.9 GB	153–229 tok/s	32K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 126.9 GB	153–229 tok/s	32K	One GPU
Runs well	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 126.9 GB	154–231 tok/s	32K	One GPU
Runs well	Gemma 4 E2B Google	5.1B	BF16 (native)maker’s file	10.1 / 126.9 GB	233–349 tok/s	125K	One GPU
Runs well	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 126.9 GB	221–331 tok/s	256K	One GPU
Runs well	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 126.9 GB	224–337 tok/s	31K	One GPU
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	BF16 (native)maker’s file	9.4 / 126.9 GB	250–375 tok/s	256K	One GPU
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	BF16 (native)maker’s file	9.9 / 126.9 GB	238–357 tok/s	250K	One GPU
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 126.9 GB	259–389 tok/s	256K	One GPU
Runs well	Qwen3-4B Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 126.9 GB	259–389 tok/s	128K	One GPU
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 126.9 GB	862–1292 tok/s	8K	One GPU
Runs well	Granite-4.0-H-Micro IBM	3.2B	BF16 (native)maker’s file	6.5 / 126.9 GB	372–558 tok/s	128K	One GPU
Runs well	Qwen3-1.7B Alibaba Qwen	2B	BF16 (native)maker’s file	5.2 / 126.9 GB	480–720 tok/s	40K	One GPU
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	BF16 (native)maker’s file	4.0 / 126.9 GB	633–950 tok/s	125K	One GPU
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 126.9 GB	753–1129 tok/s	128K	One GPU
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 126.9 GB	982–1474 tok/s	40K	One GPU
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 126.9 GB	1522–2283 tok/s	256K	One GPU
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 126.9 GB	1126–1689 tok/s	32K	One GPU
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 126.9 GB	780–1170 tok/s	8K	One GPU
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 126.9 GB	780–1170 tok/s	8K	One GPU
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 126.9 GB	1725–2588 tok/s	512	One GPU
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 126.9 GB	2122–3183 tok/s	514	One GPU
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 126.9 GB	5254–7880 tok/s	512	One GPU
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 126.9 GB	16795–25192 tok/s	512	One GPU
Needs system memory	GLM-5.3-Flash Zhipu AI	321.3B / 18B	Q4_0	177.1 GB, 52.4 in system memory	14–20 tok/s	—	14/45 layers in system memory
Needs system memory	MiMo-V2.5 Xiaomi	310.8B / 15B	Q4_0	172.1 GB, 47.5 in system memory	17–26 tok/s	—	14/48 layers in system memory
Needs system memory	DeepSeek-V4-Flash (2026-07-31) DeepSeek	304.2B	IQ4_XS	158.7 GB, 35.0 in system memory	10–15 tok/s	—	10/43 layers in system memory
Needs system memory	Hy3 Tencent	298.8B / 21B	Q4_0	166.9 GB, 41.1 in system memory	14–21 tok/s	—	21/80 layers in system memory
Needs system memory	DeepSeek-V4-Flash (2026-04-24) DeepSeek	290.9B / 13B	FP8 (native)maker’s file	156.8 GB, 31.1 in system memory	28–42 tok/s	—	9/43 layers in system memory
Needs system memory	DeepSeek-V4-Flash DeepSeek	290.9B / 13B	FP8 (native)maker’s file	156.8 GB, 31.1 in system memory	28–42 tok/s	—	9/43 layers in system memory
Needs system memory	ERNIE-5.5-Flash-Base Baidu	286.2B	Q4_K_M	170.4 GB, 45.2 in system memory	speed not estimated	—	12/43 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