Hardware / NVIDIA /H200 141GB SXM

NVIDIA · GPU

H200 141GB SXM

Runs 165 models fully in memory, 15 more with CPU offload. 2 of those sit close enough to 141 GB that our size estimate is what decides them.

Memory

141 GB

Bandwidth

4800 GB/s

Runs

165

01

Specifications

Memory

141 GB

Decides which models fit at all.

Memory bandwidth

4800 GB/s

How fast it can read the model. Sets the speed of the reply.

Compute

989 TFLOPS

Trillions of half-precision sums a second. Sets how fast it reads a long prompt, not how fast it replies.

Power draw

700 W

At full load, for sizing a power supply.

MSRP

$35,000

What the maker asked for it new. We hold no used or street prices, so this is not what one costs today.

Released

Apr 1, 2024

Architecture

Hopper

02

What it runs

Best quant per model. Text models first, then speech, then what does not fit.

What is quantisation? →

ModelParamsContextSpeedVerdict

Nex-N2-Mini35.1B262K153 tok/sFits in memory Granite 4.1 8B8.8B131K411 tok/sFits in memory Qwen3.6 35B A3B36B262K1530 tok/sFits in memory Gemma 4 26B A4B25.8B262K1147 tok/sFits in memory Gemma 4 31B31.3B66K202 tok/sFits in memory Qwen3.5-9B9.7B262K557 tok/sFits in memory Qwen3.5-27B27.8B262K130 tok/sFits in memory Qwen3.5-122B-A10B125B262K459 tok/sFits in memory GLM 4.7 Flash31.2B131K173 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B262K1024 tok/sFits in memory Ministral 3 14B 251213.9B262K260 tok/sFits in memory Ministral 3 8B 25128.9B262K607 tok/sFits in memory Ministral 3 3B 25123.8B131K951 tok/sFits in memory Olmo 3 32B Think32.2B66K168 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K1275 tok/sFits in memory Qwen3 VL 32B Instruct33.4B131K162 tok/sFits in memory Granite 4.0 Micro3.2B66K1687 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K720 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B262K1795 tok/sFits in memory Cydonia 24B V4.123.6B131K229 tok/sFits in memory Qwen3 Next 80B A3B Thinking81.3B262K1024 tok/sFits in memory gpt-oss-120b120B131K900 tok/sFits in memory GLM 4.5 Air111B131K449 tok/sFits in memory UI-TARS 7B8.3B66K435 tok/sFits in memory Uncensored24B66K225 tok/sFits in memory Hunyuan A13B Instruct80.4B131K236 tok/sFits in memory Mistral Small 3.2 24B24B131K264 tok/sFits in memory Llama Guard 4 12B12B262K450 tok/sFits in memory Qwen3 14B14.8B131K244 tok/sFits in memory Gemma 3 12B12.2B131K519 tok/sFits in memory Gemma 3 27B27.4B262K231 tok/sFits in memory Rocinante 12B12.2B66K296 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K1129 tok/sFits in memory Mistral Nemo12.2B131K296 tok/sFits in memory Mixtral 8x22B Instruct141B66K138 tok/sFits in memory Laguna XS 2.133.4B262K137 tok/sFits in memory Qwen3.6 27B27.8B262K130 tok/sFits in memory Qwen3.5-35B-A3B36B262K1795 tok/sFits in memory Qwen3 VL 8B Instruct8.8B262K614 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B262K1795 tok/sFits in memory Qwen3 Next 80B A3B Instruct81.3B262K1795 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K1024 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B262K1024 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B262K1530 tok/sFits in memory Qwen3 8B8.2B131K772 tok/sFits in memory Qwen3 32B32.8B131K165 tok/sFits in memory Mistral Small 3.1 24B24B66K225 tok/sFits in memory Gemma 3 4B4.3B131K1256 tok/sFits in memory Reka Flash 320.9B66K303 tok/sFits in memory Llama 3.1 8B Instruct8B131K675 tok/sFits in memory Muse Glimmer 30B29.8B131K121 tok/sFits in memory Nemotron 3.5 Lightning31.6B262K170 tok/sFits in memory Qwen3.8 27B27.8B262K194 tok/sFits in memory Granite 4.2 8B8.8B131K411 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K1256 tok/sFits in memory Ternary Bonsai 2 27B27B262K200 tok/sFits in memory Nex-N2.5-Mini35.1B262K131 tok/sFits in memory Gemma 3n 4B7.8B33K692 tok/sFits in memory Skyfall 36B V236.9B33K172 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B33K165 tok/sFits in memory UnslopNemo 12B12.2B33K443 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K5278 tok/sFits in memory Mistral Small 323.6B33K268 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K476 tok/sFits in memory Reka Edge7.1B16K892 tok/sFits in memory Voxtral Small 24B 250724.3B16K222 tok/sFits in memory Phi 414.7B16K431 tok/sFits in memory Hermes 4 70B70.6B131K90 tok/sFits in memory Qwen2.5 VL 72B Instruct73.4B66K86 tok/sFits in memory Llama 3.3 Euryale 70B70.6B131K90 tok/sFits in memory Llama 3.1 Euryale 70B v2.270.6B131K90 tok/sFits in memory Hermes 3 70B Instruct70.6B131K90 tok/sFits in memory Llama 3.1 70B Instruct70.6B131K90 tok/sFits in memory Llama 3.3 70B Instruct70.6B131K90 tok/sFits in memory Llama 3 8B Lunaris8B8K792 tok/sFits in memory MythoMax 13B13B8K278 tok/sFits in memory Gemma 2 27B27.2B8K233 tok/sFits in memory Hy-MT2-1.8B2B8K2295 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K1795 tok/sFits in memory Hy-MT2-7B8B8K574 tok/sFits in memory Qwen2.5 72B Instruct72.7B33K87 tok/sFits in memory ReMM SLERP 13B13B4K415 tok/sFits in memory Qwen3 Coder Next79.7B262K68 tok/sFits in memory Magnum v4 72B72.7B16K87 tok/sFits in memory Llama 4 Scout109B262K58 tok/sFits in memory Command A111B131K57 tok/sFits in memory Ling-2.6-flash107B131K50 tok/sFits in memory Devstral 2 2512125B131K51 tok/sFits in memory GLM 4.6V108B131K50 tok/sFits in memory GLM 4.5V108B66K50 tok/sFits in memory R1 Distill Llama 70B70.6B8K90 tok/sFits in memory Mistral Medium 3.5128B131K50 tok/sFits in memory Laguna S 2.1118B131K46 tok/sFits in memory Mistral Small 4119B66K45 tok/sFits in memory Nemotron 3 Super124B262K44 tok/sFits in memory Ling-3.0-flash128B66K42 tok/sFits in memory Step 3.5 Flash199B33K27 tok/sFits in memoryest Step 3.7 Flash201B16K27 tok/sFits in memoryest

Speech models it runs67 modelsTranscription and speech models that fit in memory. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.

Niagara 19m Batch.en20M316701 tok/sFits in memory Niagara 38m Batch.en38M95108 tok/sFits in memory Higgs Audio v3 8b STT v28.9B712 tok/sFits in memory Higgs Audio v3 STT2.7B1339 tok/sFits in memory Cohere Transcribe 03 20262.1B1721 tok/sFits in memory Distil Large v3.50.8B4518 tok/sFits in memory Lite Whisper Large v3 Acc1.4B3856 tok/sFits in memory Owsm CTC v3.1 1B1.1B5758 tok/sFits in memory Owsm CTC v3.2 ft 1B1B3614 tok/sFits in memory Owsm CTC v4 1B1B6334 tok/sFits in memory Hubert Large Ls960 ft0.3B11294 tok/sFits in memory MMS 1b All1B5399 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B11294 tok/sFits in memory Hojo ASR V15.2B1042 tok/sFits in memory Granite 4.0 1b Speech2.3B1571 tok/sFits in memory Granite Speech 3.3 2b3B2111 tok/sFits in memory Granite Speech 3.3 8b8.6B737 tok/sFits in memory Granite Speech 4.1 2b2.3B2754 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B2754 tok/sFits in memory STT 2.6b en2.6B2436 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K1131 tok/sFits in memory VibeVoice ASR HF8.3B435 tok/sFits in memory Voxtral Mini 3B 25074.7B769 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B821 tok/sFits in memory Canary 180m Flash0.2B29994 tok/sFits in memory Canary 1b1B3614 tok/sFits in memory Canary 1b Flash0.8B4518 tok/sFits in memory Canary 1b v21B6334 tok/sFits in memory Canary Qwen 2.5b2.6B1390 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B10557 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B8998 tok/sFits in memory Parakeet CTC 0.6b0.6B8998 tok/sFits in memory Parakeet CTC 1.1b1.1B4908 tok/sFits in memory Parakeet RNNT 0.6b0.6B6024 tok/sFits in memory Parakeet RNNT 1.1b1.1B4908 tok/sFits in memory Parakeet TDT CTC 110m0.1B57582 tok/sFits in memory Parakeet TDT 0.6b v20.6B6024 tok/sFits in memory Parakeet TDT 0.6b v30.6B10557 tok/sFits in memory Parakeet TDT 1.1b1.1B3286 tok/sFits in memory Nyra Health CrisperWhisper1.6B2259 tok/sFits in memory Whisper Large v31.5B3599 tok/sFits in memory Whisper Large v3 Turbo0.8B6749 tok/sFits in memory MOSS Transcribe Diarize0.9B5999 tok/sFits in memory Qwen3 ASR 0.6B0.9B7038 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B7918 tok/sFits in memory Qwen3 ASR 1.7B2.3B2347 tok/sFits in memory Qwen3 ASR 1.7B HF2B1807 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B18617 tok/sFits in memory Zipformer Transducer XL 290M0.3B12463 tok/sFits in memory ASR Conformer Largescaleasr0.5B7529 tok/sFits in memory GLM ASR Nano 25122.3B2754 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B10798 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B12668 tok/sFits in memory Fun ASR Nano 2512 HF0.8B7918 tok/sFits in memory Gemma 4 12B it12B450 tok/sFits in memory Gemma 4 E2B it5.1B709 tok/sFits in memory Gemma 4 E4B it8B131K675 tok/sFits in memory Niagara 9m Batch.en9M401569 tok/sFits in memory Niagara 84m Batch.en84M43025 tok/sFits in memory ARK ASR 0.6B1.3B33K4153 tok/sFits in memory ARK ASR 3B4.1B33K1545 tok/sFits in memory Audio8 ASR 0.1B0.3B33K12047 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K2639 tok/sFits in memory Moonshine Streaming Medium0.3B4K12047 tok/sFits in memory Moonshine Streaming Small0.1B4K53990 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory15 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Hy3299B—no speed estimateSpills to system RAMest MiniMax M2.7229B—no speed estimateSpills to system RAM Qwen3 VL 235B A22B Thinking236B—no speed estimateSpills to system RAM Laguna M.1226B—no speed estimateSpills to system RAM DeepSeek V4 Flash291B—no speed estimateSpills to system RAM Hy3 preview299B—no speed estimateSpills to system RAMest MiMo-V2.5311B—no speed estimateSpills to system RAMest MiniMax M2.5229B—no speed estimateSpills to system RAM MiniMax M2.1229B—no speed estimateSpills to system RAMest Qwen3 VL 235B A22B Instruct236B—no speed estimateSpills to system RAM Qwen3 235B A22B Thinking 2507235B—no speed estimateSpills to system RAM Qwen3 235B A22B Instruct 2507235B—no speed estimateSpills to system RAM MiniMax M2229B—no speed estimateSpills to system RAM Inkling Small266B—no speed estimateSpills to system RAMest DeepSeek V4 Flash Vision Exp305B—no speed estimateSpills to system RAMest

Too large for this device44 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

GLM 5.3 Flash321B—no speed estimateToo largeest Trinity Large Thinking399B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Hermes 4 405B406B—no speed estimateToo large GLM 4.6357B—no speed estimateToo large GLM 4.7358B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large R1 0528685B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large Inkling952B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large Kimi K2.61.1T—no speed estimateToo large GLM 5754B—no speed estimateToo large Hy4 preview780B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 165 fit in memory, 15 spill into system memory and 44 are too large. Every one of them is on this page.

03

Other Hopper cards

The same generation in other memory sizes. Memory is what decides which models fit.

H100 80GB SXM80 GB · less memory

Something wrong on this page? Tell us