Which model for 8 × H200 · 1128 Go?
1128 GB usable for the model. 114 open-weight models fit in memory.
The margin goes to context: count ~1 GB per 8k tokens for a 7B model. A small margin means a short context.
Unlocked by this setup
These models fit on no smaller setup in the catalogue (the next one down offers 640 usable GB), even in their lightest quantization.
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| Kimi K2Moonshot AI · 1026B | 1418 | Q4_K_M | 645 Go | +483 Go | comfortable | Hugging Face ↗ |
Also fit on a smaller setup
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| GLM-5.3Zhipu AI · 753B | 1478 | Q8_0 | 888 Go | +240 Go | tight | Hugging Face ↗ |
| GLM-5.2Zhipu AI · 754B | 1475 | Q8_0 | 889 Go | +239 Go | tight | Hugging Face ↗ |
| GLM-5Zhipu AI · 744B | 1458 | Q8_0 | 878 Go | +250 Go | tight | Hugging Face ↗ |
| Gemma 4 31BGoogle · 31B | 1452 | FP16 | 70 Go | +1058 Go | comfortable | Hugging Face ↗ |
| Qwen3.5 397B-A17BAlibaba · 397B | 1442 | FP16 | 875 Go | +253 Go | tight | Hugging Face ↗ |
| DeepSeek V4-FlashDeepSeek · 284B | 1439 | Q4_K_MFP16 also fits · 627 Go | 180 Go | +948 Go | comfortable | ollama run deepseek-v4-flash |
| Gemma 4 26B-A4BGoogle · 26B | 1438 | FP16 | 59 Go | +1069 Go | comfortable | Hugging Face ↗ |
| Mistral Medium 3.5Mistral AI · 128B | 1426 | FP16 | 284 Go | +844 Go | comfortable | Hugging Face ↗ |
| Nemotron 3 Ultra 550B-A55BNVIDIA · 550B | 1426 | Q8_0 | 649 Go | +479 Go | comfortable | Hugging Face ↗ |
| Mistral Large 3Mistral AI · 675B | 1414 | Q8_0 | 796 Go | +332 Go | tight | Hugging Face ↗ |
| GLM-4.5Z.ai · 355B | 1411 | FP16 | 783 Go | +345 Go | comfortable | Hugging Face ↗ |
| DeepSeek-R1DeepSeek · 671B | 1398 | Q4_K_MQ8_0 also fits · 792 Go | 423 Go | +705 Go | comfortable | ollama run deepseek-r1:671b |
| DeepSeek V3DeepSeek · 685B | 1395 | Q4_K_MQ8_0 also fits · 808 Go | 431 Go | +697 Go | comfortable | ollama run deepseek-v3 |
| Qwen3-Coder 480BAlibaba · 480B | 1388 | Q4_K_MFP16 also fits · 1058 Go | 303 Go | +825 Go | comfortable | ollama run qwen3-coder:480b |
| Qwen3 235B-A22BAlibaba · 235B | 1375 | Q4_K_MFP16 also fits · 519 Go | 149 Go | +979 Go | comfortable | ollama run qwen3:235b |
| GLM-4.5 AirZ.ai · 106B | 1373 | FP16 | 235 Go | +893 Go | comfortable | Hugging Face ↗ |
| Gemma 3 27BGoogle · 27B | 1365 | Q4_K_MFP16 also fits · 61 Go | 19 Go | +1109 Go | comfortable | ollama run gemma3:27b |
| Nemotron 3 Super 120B-A12BNVIDIA · 120B | 1360 | FP16 | 266 Go | +862 Go | comfortable | Hugging Face ↗ |
| Mistral Small 3.2Mistral AI · 24B | 1356 | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1111 Go | comfortable | ollama run mistral-small3.2 |
| gpt-oss-120bOpenAI · 117B | 1352 | MXFP4 | 73 Go | +1055 Go | comfortable | ollama run gpt-oss:120b |
| Qwen3 32BAlibaba · 32.8B | 1347 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1105 Go | comfortable | ollama run qwen3:32b |
| Gemma 3 12BGoogle · 12B | 1342 | Q4_K_MFP16 also fits · 28 Go | 9 Go | +1119 Go | comfortable | ollama run gemma3:12b |
| QwQ 32BAlibaba · 32.8B | 1336 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1105 Go | comfortable | ollama run qwq |
| Llama 4 MaverickMeta · 400B | 1327 | Q4_K_MFP16 also fits · 882 Go | 253 Go | +875 Go | comfortable | ollama run llama4:maverick |
| Llama 4 ScoutMeta · 109B | 1322 | Q4_K_MFP16 also fits · 242 Go | 70 Go | +1058 Go | comfortable | ollama run llama4:scout |
| Gemma 3n E4BGoogle · 4B | 1318 | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1123 Go | comfortable | ollama run gemma3n:e4b |
| Llama 3.3 70BMeta · 70.6B | 1318 | Q4_K_MFP16 also fits · 157 Go | 46 Go | +1082 Go | comfortable | ollama run llama3.3:70b |
| gpt-oss-20bOpenAI · 21B | 1317 | MXFP4 | 17 Go | +1111 Go | comfortable | ollama run gpt-oss:20b |
| Nemotron 3 Nano 30B-A3BNVIDIA · 30B | 1314 | FP16 | 68 Go | +1060 Go | comfortable | Hugging Face ↗ |
| Granite 4.1 8BIBM · 8B | 1304 | FP16 | 20 Go | +1108 Go | comfortable | Hugging Face ↗ |
| Gemma 3 4BGoogle · 4B | 1303 | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1123 Go | comfortable | ollama run gemma3:4b |
| Qwen2.5 72BAlibaba · 72.7B | 1303 | Q4_K_MFP16 also fits · 162 Go | 48 Go | +1080 Go | comfortable | ollama run qwen2.5:72b |
| Llama 3.1 Nemotron 70BNVIDIA · 70.6B | 1299 | Q4_K_MFP16 also fits · 157 Go | 46 Go | +1082 Go | comfortable | ollama run nemotron:70b |
| Qwen2.5-Coder 32BAlibaba · 32.8B | 1271 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1105 Go | comfortable | ollama run qwen2.5-coder:32b |
| Aya Expanse 32BCohere · 32.3B | 1267 | Q4_K_MFP16 also fits · 73 Go | 22 Go | +1106 Go | comfortable | ollama run aya-expanse:32b |
| Command R+Cohere · 104B | 1262 | Q4_K_MFP16 also fits · 231 Go | 67 Go | +1061 Go | comfortable | ollama run command-r-plus |
| Phi-4Microsoft · 14.7B | 1256 | Q4_K_MFP16 also fits · 34 Go | 11 Go | +1117 Go | comfortable | ollama run phi4 |
| Phi-4 ReasoningMicrosoft · 14.7B | 1256 | Q4_K_MFP16 also fits · 34 Go | 11 Go | +1117 Go | comfortable | ollama run phi4-reasoning |
| OLMo 2 32BAllen AI · 32B | 1252 | FP16 | 72 Go | +1056 Go | comfortable | Hugging Face ↗ |
| CodestralMistral AI · 22.2B | 1240 | Q4_K_MFP16 also fits · 51 Go | 16 Go | +1112 Go | comfortable | ollama run codestral |
| Ministral 8BMistral AI · 8.02B | 1238 | FP16 | 20 Go | +1108 Go | comfortable | Hugging Face ↗ |
| Llama 3.1 8BMeta · 8.03B | 1211 | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run llama3.1:8b |
| Mixtral 8x7BMistral AI · 46.7B | 1197 | Q4_K_MFP16 also fits · 105 Go | 31 Go | +1097 Go | comfortable | ollama run mixtral:8x7b |
| Llama 3.2 3BMeta · 3.21B | 1167 | Q4_K_MFP16 also fits · 9 Go | 4 Go | +1124 Go | comfortable | ollama run llama3.2:3b |
| Llama 3.2 1BMeta · 1.24B | 1111 | Q4_K_MFP16 also fits · 5 Go | 3 Go | +1125 Go | comfortable | ollama run llama3.2:1b |
| Mistral 7BMistral AI · 7.25B | 1110 | Q4_K_MFP16 also fits · 18 Go | 7 Go | +1121 Go | comfortable | ollama run mistral:7b |
Not yet ranked by the Arena
No Arena Elo linked: recent release, model absent from the Arena, or a match we have not made yet.
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| Qwen3 0.6BAlibaba · 0.6B | — | Q4_K_MFP16 also fits · 3 Go | 2 Go | +1126 Go | comfortable | ollama run qwen3:0.6b |
| Gemma 3 1BGoogle · 1B | — | Q4_K_MFP16 also fits · 4 Go | 3 Go | +1125 Go | comfortable | ollama run gemma3:1b |
| Phi-4 MiniMicrosoft · 3.8B | — | Q4_K_MFP16 also fits · 10 Go | 4 Go | +1124 Go | comfortable | ollama run phi4-mini |
| Qwen3 4BAlibaba · 4.02B | — | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1123 Go | comfortable | ollama run qwen3:4b |
| Gemma 4 E2BGoogle · 2B | — | FP16 | 6 Go | +1122 Go | comfortable | Hugging Face ↗ |
| CodeGemma 7BGoogle · 8.5B | — | Q4_K_MFP16 also fits · 21 Go | 7 Go | +1121 Go | comfortable | ollama run codegemma |
| Command R7BCohere · 8B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run command-r7b |
| DeepSeek-R1 Distill 8BDeepSeek · 8.03B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run deepseek-r1:8b |
| Granite 3.3 8BIBM · 8.1B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run granite3.3:8b |
| Hermes 3 8BNous Research · 8.03B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run hermes3:8b |
| MiniCPM5-2BOpenBMB · 2.5B | — | FP16 | 7 Go | +1121 Go | comfortable | Hugging Face ↗ |
| Qwen3 8BAlibaba · 8.2B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1121 Go | comfortable | ollama run qwen3:8b |
| Falcon 3 10BTII · 10.3B | — | Q4_K_MFP16 also fits · 25 Go | 8 Go | +1120 Go | comfortable | ollama run falcon3:10b |
| Granite 4.1 3BIBM · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| Ministral 3 3BMistral AI · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| SmolLM3 3BHugging Face · 3.1B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| Mistral Nemo 12BMistral AI · 12.2B | — | Q4_K_MFP16 also fits · 29 Go | 10 Go | +1118 Go | comfortable | ollama run mistral-nemo |
| Gemma 4 E4BGoogle · 4B | — | FP16 | 11 Go | +1117 Go | comfortable | Hugging Face ↗ |
| Qwen3 14BAlibaba · 14.8B | — | Q4_K_MFP16 also fits · 35 Go | 11 Go | +1117 Go | comfortable | ollama run qwen3:14b |
| DeepSeek-Coder-V2 LiteDeepSeek · 15.7B | — | Q4_K_MFP16 also fits · 37 Go | 12 Go | +1116 Go | comfortable | ollama run deepseek-coder-v2:16b |
| StarCoder 2BigCode · 16B | — | Q4_K_MFP16 also fits · 37 Go | 12 Go | +1116 Go | comfortable | ollama run starcoder2:15b |
| Devstral SmallMistral AI · 24B | — | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1111 Go | comfortable | ollama run devstral |
| Lucie 7BOpenLLM France · 6.7B | — | FP16 | 17 Go | +1111 Go | comfortable | Hugging Face ↗ |
| Magistral SmallMistral AI · 24B | — | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1111 Go | comfortable | ollama run magistral |
| OLMo 3 7BAllen AI · 7B | — | FP16 | 17 Go | +1111 Go | comfortable | Hugging Face ↗ |
| Apertus 8BSwiss AI · 8B | — | FP16 | 20 Go | +1108 Go | comfortable | Hugging Face ↗ |
| Ministral 3 8BMistral AI · 8B | — | FP16 | 20 Go | +1108 Go | comfortable | Hugging Face ↗ |
| InternLM3 8BShanghai AI Lab · 8.8B | — | FP16 | 21 Go | +1107 Go | comfortable | Hugging Face ↗ |
| EuroLLM 9BUTTER Project · 9.15B | — | FP16 | 22 Go | +1106 Go | comfortable | Hugging Face ↗ |
| DeepSeek-R1 Distill 32BDeepSeek · 32.8B | — | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1105 Go | comfortable | ollama run deepseek-r1:32b |
| Gemma 4 12BGoogle · 12B | — | FP16 | 28 Go | +1100 Go | comfortable | Hugging Face ↗ |
| Ministral 3 14BMistral AI · 14B | — | FP16 | 33 Go | +1095 Go | comfortable | Hugging Face ↗ |
| Qwen3.6 27BAlibaba · 27B | — | FP16 | 61 Go | +1067 Go | comfortable | Hugging Face ↗ |
| Qwen3.8 27BAlibaba · 27B | — | FP16 | 61 Go | +1067 Go | comfortable | Hugging Face ↗ |
| Qwen3.6 35B-A3BAlibaba · 35B | — | FP16 | 79 Go | +1049 Go | comfortable | Hugging Face ↗ |
| Mistral Small 4Mistral AI · 119B | — | FP16 | 264 Go | +864 Go | comfortable | Hugging Face ↗ |
| DeepSeek V4.1-FlashDeepSeek · 552B | — | FP8 | 563 Go | +565 Go | comfortable | Hugging Face ↗ |
| Kimi K2.7 CodeMoonshot AI · 1000B | — | Q4_K_M | 629 Go | +499 Go | comfortable | Hugging Face ↗ |
Image, video, audio and 3D
These models do not generate text, so the text Arena does not rank them. Indicative order, not a quality ranking.
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| Kokoro-82MHexgrad · 0.08B | — | FP16 | 2 Go | +1126 Go | comfortable | Hugging Face ↗ |
| ChatterboxResemble AI · 0.5B | — | FP16 | 3 Go | +1125 Go | comfortable | Hugging Face ↗ |
| Parakeet TDT 0.6B v3NVIDIA · 0.6B | — | FP16 | 3 Go | +1125 Go | comfortable | Hugging Face ↗ |
| TripoSRStability AI · 0.5B | — | FP16 | 3 Go | +1125 Go | comfortable | Hugging Face ↗ |
| Stable Fast 3DStability AI · 1B | — | FP16 | 4 Go | +1124 Go | comfortable | Hugging Face ↗ |
| TRELLISMicrosoft · 1.2B | — | FP16 | 5 Go | +1123 Go | comfortable | Hugging Face ↗ |
| Whisper large-v3OpenAI · 1.55B | — | FP16 | 5 Go | +1123 Go | comfortable | Hugging Face ↗ |
| Dia 1.6BNari Labs · 1.6B | — | FP16 | 6 Go | +1122 Go | comfortable | Hugging Face ↗ |
| Hunyuan3D 2.1Tencent · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| Orpheus 3BCanopy Labs · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| Voxtral Mini 3BMistral AI · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| YuE2-3Bm-a-p (Multimodal Art Projection) · 3B | — | FP16 | 9 Go | +1119 Go | comfortable | Hugging Face ↗ |
| FLUX.2 [klein] 4BBlack Forest Labs · 4B | — | FP16 | 11 Go | +1117 Go | comfortable | Hugging Face ↗ |
| TRELLIS.2Microsoft · 4B | — | FP16 | 11 Go | +1117 Go | comfortable | Hugging Face ↗ |
| CogVideoX 5BZhipu AI · 5B | — | FP16 | 13 Go | +1115 Go | comfortable | Hugging Face ↗ |
| Wan 2.2 5BAlibaba · 5B | — | FP16 | 13 Go | +1115 Go | comfortable | Hugging Face ↗ |
| Ming-Image 0.1 DesignAnt Group · 6B | — | FP16 | 15 Go | +1113 Go | comfortable | Hugging Face ↗ |
| Z-Image TurboAlibaba · 6B | — | FP16 | 15 Go | +1113 Go | comfortable | Hugging Face ↗ |
| HunyuanVideo 1.5Tencent · 8.3B | — | FP16 | 20 Go | +1108 Go | comfortable | Hugging Face ↗ |
| GLM-ImageZhipu AI · 9B | — | FP16 | 22 Go | +1106 Go | comfortable | Hugging Face ↗ |
| Mochi 1Genmo · 10B | — | FP16 | 24 Go | +1104 Go | comfortable | Hugging Face ↗ |
| FLUX.1 [dev]Black Forest Labs · 12B | — | FP16 | 28 Go | +1100 Go | comfortable | Hugging Face ↗ |
| HiDream-I1HiDream · 17B | — | FP16 | 39 Go | +1089 Go | comfortable | Hugging Face ↗ |
| Qwen-Image 2512Alibaba · 20B | — | FP16 | 46 Go | +1082 Go | comfortable | Hugging Face ↗ |
| LTX-2.3Lightricks · 22B | — | FP16 | 50 Go | +1078 Go | comfortable | Hugging Face ↗ |
| Voxtral Small 24BMistral AI · 24B | — | FP16 | 55 Go | +1073 Go | comfortable | Hugging Face ↗ |
| Wan 2.2 A14BAlibaba · 27B | — | FP16 | 61 Go | +1067 Go | comfortable | Hugging Face ↗ |
| FLUX.2 [dev]Black Forest Labs · 32B | — | FP16 | 72 Go | +1056 Go | comfortable | Hugging Face ↗ |
| HunyuanImage 3.0Tencent · 80B | — | FP16 | 178 Go | +950 Go | comfortable | Hugging Face ↗ |
An “ollama run” command without a suffix pulls the Q4_K_M build from the Ollama library: the row then shows that quantization and its memory, and flags whether FP16 or Q8_0 would also fit. Exception: a model published in a native format (MXFP4 for gpt-oss, FP8 for DeepSeek V4.1) exists in one build only, which is what the command loads. via Hugging Face or an explicit Ollama tag.
Share this verdict
One link, the same shortlist, the same reasons.