Which model for 8 × B200 · 1440 Go?
1440 GB usable for the model. 119 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 1128 usable GB), even in their lightest quantization.
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| Mistral Large 4Mistral AI · 1000B | 1420 | FP8 | 1168 Go | +272 Go | tight | Hugging Face ↗ |
Also fit on a smaller setup
| Model | Elo | Quantization | RAM required | Margin | Memory headroom | Run |
|---|---|---|---|---|---|---|
| GLM-5.3Zhipu AI · 753B | 1482 | Q8_0 | 888 Go | +552 Go | comfortable | Hugging Face ↗ |
| DeepSeek V4.1-FlashDeepSeek · 552B | 1475 | FP8 | 563 Go | +877 Go | comfortable | Hugging Face ↗ |
| GLM-5.2Zhipu AI · 754B | 1475 | Q8_0 | 889 Go | +551 Go | comfortable | Hugging Face ↗ |
| GLM-5Zhipu AI · 744B | 1457 | Q8_0 | 878 Go | +562 Go | comfortable | Hugging Face ↗ |
| Gemma 4 31BGoogle · 31B | 1452 | FP16 | 70 Go | +1370 Go | comfortable | Hugging Face ↗ |
| Qwen3.5 397B-A17BAlibaba · 397B | 1441 | FP16 | 875 Go | +565 Go | comfortable | Hugging Face ↗ |
| DeepSeek V4-FlashDeepSeek · 284B | 1439 | Q4_K_MFP16 also fits · 627 Go | 180 Go | +1260 Go | comfortable | ollama run deepseek-v4-flash |
| Gemma 4 26B-A4BGoogle · 26B | 1437 | FP16 | 59 Go | +1381 Go | comfortable | Hugging Face ↗ |
| Qwen3.8 27BAlibaba · 27B | 1434 | FP16 | 61 Go | +1379 Go | comfortable | Hugging Face ↗ |
| Mistral Medium 3.5Mistral AI · 128B | 1426 | FP16 | 284 Go | +1156 Go | comfortable | Hugging Face ↗ |
| Nemotron 3 Ultra 550B-A55BNVIDIA · 550B | 1426 | FP16 | 1212 Go | +228 Go | tight | Hugging Face ↗ |
| Kimi K2Moonshot AI · 1026B | 1418 | Q8_0 | 1210 Go | +230 Go | tight | Hugging Face ↗ |
| Mistral Large 3Mistral AI · 675B | 1415 | Q8_0 | 796 Go | +644 Go | comfortable | Hugging Face ↗ |
| GLM-4.5Z.ai · 355B | 1411 | FP16 | 783 Go | +657 Go | comfortable | Hugging Face ↗ |
| DeepSeek-R1DeepSeek · 671B | 1398 | Q4_K_MQ8_0 also fits · 792 Go | 423 Go | +1017 Go | comfortable | ollama run deepseek-r1:671b |
| DeepSeek V3DeepSeek · 685B | 1395 | Q4_K_MQ8_0 also fits · 808 Go | 431 Go | +1009 Go | comfortable | ollama run deepseek-v3 |
| Qwen3-Coder 480BAlibaba · 480B | 1387 | Q4_K_MFP16 also fits · 1058 Go | 303 Go | +1137 Go | comfortable | ollama run qwen3-coder:480b |
| Qwen3 235B-A22BAlibaba · 235B | 1375 | Q4_K_MFP16 also fits · 519 Go | 149 Go | +1291 Go | comfortable | ollama run qwen3:235b |
| GLM-4.5 AirZ.ai · 106B | 1373 | FP16 | 235 Go | +1205 Go | comfortable | Hugging Face ↗ |
| Gemma 3 27BGoogle · 27B | 1365 | Q4_K_MFP16 also fits · 61 Go | 19 Go | +1421 Go | comfortable | ollama run gemma3:27b |
| Nemotron 3 Super 120B-A12BNVIDIA · 120B | 1360 | FP16 | 266 Go | +1174 Go | comfortable | Hugging Face ↗ |
| Mistral Small 3.2Mistral AI · 24B | 1356 | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1423 Go | comfortable | ollama run mistral-small3.2 |
| gpt-oss-120bOpenAI · 117B | 1352 | MXFP4 | 73 Go | +1367 Go | comfortable | ollama run gpt-oss:120b |
| Qwen3 32BAlibaba · 32.8B | 1347 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1417 Go | comfortable | ollama run qwen3:32b |
| Gemma 3 12BGoogle · 12B | 1342 | Q4_K_MFP16 also fits · 28 Go | 9 Go | +1431 Go | comfortable | ollama run gemma3:12b |
| QwQ 32BAlibaba · 32.8B | 1336 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1417 Go | comfortable | ollama run qwq |
| Llama 4 MaverickMeta · 400B | 1327 | Q4_K_MFP16 also fits · 882 Go | 253 Go | +1187 Go | comfortable | ollama run llama4:maverick |
| Llama 4 ScoutMeta · 109B | 1322 | Q4_K_MFP16 also fits · 242 Go | 70 Go | +1370 Go | comfortable | ollama run llama4:scout |
| Gemma 3n E4BGoogle · 4B | 1318 | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1435 Go | comfortable | ollama run gemma3n:e4b |
| gpt-oss-20bOpenAI · 21B | 1318 | MXFP4 | 17 Go | +1423 Go | comfortable | ollama run gpt-oss:20b |
| Llama 3.3 70BMeta · 70.6B | 1318 | Q4_K_MFP16 also fits · 157 Go | 46 Go | +1394 Go | comfortable | ollama run llama3.3:70b |
| Nemotron 3 Nano 30B-A3BNVIDIA · 30B | 1314 | FP16 | 68 Go | +1372 Go | comfortable | Hugging Face ↗ |
| Granite 4.1 8BIBM · 8B | 1304 | FP16 | 20 Go | +1420 Go | comfortable | Hugging Face ↗ |
| Gemma 3 4BGoogle · 4B | 1303 | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1435 Go | comfortable | ollama run gemma3:4b |
| Qwen2.5 72BAlibaba · 72.7B | 1303 | Q4_K_MFP16 also fits · 162 Go | 48 Go | +1392 Go | comfortable | ollama run qwen2.5:72b |
| Llama 3.1 Nemotron 70BNVIDIA · 70.6B | 1299 | Q4_K_MFP16 also fits · 157 Go | 46 Go | +1394 Go | comfortable | ollama run nemotron:70b |
| Qwen2.5-Coder 32BAlibaba · 32.8B | 1271 | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1417 Go | comfortable | ollama run qwen2.5-coder:32b |
| Aya Expanse 32BCohere · 32.3B | 1267 | Q4_K_MFP16 also fits · 73 Go | 22 Go | +1418 Go | comfortable | ollama run aya-expanse:32b |
| Command R+Cohere · 104B | 1262 | Q4_K_MFP16 also fits · 231 Go | 67 Go | +1373 Go | comfortable | ollama run command-r-plus |
| Phi-4Microsoft · 14.7B | 1256 | Q4_K_MFP16 also fits · 34 Go | 11 Go | +1429 Go | comfortable | ollama run phi4 |
| Phi-4 ReasoningMicrosoft · 14.7B | 1256 | Q4_K_MFP16 also fits · 34 Go | 11 Go | +1429 Go | comfortable | ollama run phi4-reasoning |
| OLMo 2 32BAllen AI · 32B | 1252 | FP16 | 72 Go | +1368 Go | comfortable | Hugging Face ↗ |
| CodestralMistral AI · 22.2B | 1240 | Q4_K_MFP16 also fits · 51 Go | 16 Go | +1424 Go | comfortable | ollama run codestral |
| Ministral 8BMistral AI · 8.02B | 1238 | FP16 | 20 Go | +1420 Go | comfortable | Hugging Face ↗ |
| Llama 3.1 8BMeta · 8.03B | 1211 | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run llama3.1:8b |
| Mixtral 8x7BMistral AI · 46.7B | 1197 | Q4_K_MFP16 also fits · 105 Go | 31 Go | +1409 Go | comfortable | ollama run mixtral:8x7b |
| Llama 3.2 3BMeta · 3.21B | 1167 | Q4_K_MFP16 also fits · 9 Go | 4 Go | +1436 Go | comfortable | ollama run llama3.2:3b |
| Llama 3.2 1BMeta · 1.24B | 1111 | Q4_K_MFP16 also fits · 5 Go | 3 Go | +1437 Go | comfortable | ollama run llama3.2:1b |
| Mistral 7BMistral AI · 7.25B | 1111 | Q4_K_MFP16 also fits · 18 Go | 7 Go | +1433 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 | +1438 Go | comfortable | ollama run qwen3:0.6b |
| Gemma 3 1BGoogle · 1B | — | Q4_K_MFP16 also fits · 4 Go | 3 Go | +1437 Go | comfortable | ollama run gemma3:1b |
| Phi-4 MiniMicrosoft · 3.8B | — | Q4_K_MFP16 also fits · 10 Go | 4 Go | +1436 Go | comfortable | ollama run phi4-mini |
| Qwen3 4BAlibaba · 4.02B | — | Q4_K_MFP16 also fits · 11 Go | 5 Go | +1435 Go | comfortable | ollama run qwen3:4b |
| Gemma 4 E2BGoogle · 2B | — | FP16 | 6 Go | +1434 Go | comfortable | Hugging Face ↗ |
| CodeGemma 7BGoogle · 8.5B | — | Q4_K_MFP16 also fits · 21 Go | 7 Go | +1433 Go | comfortable | ollama run codegemma |
| Command R7BCohere · 8B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run command-r7b |
| DeepSeek-R1 Distill 8BDeepSeek · 8.03B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run deepseek-r1:8b |
| Granite 3.3 8BIBM · 8.1B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run granite3.3:8b |
| Hermes 3 8BNous Research · 8.03B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run hermes3:8b |
| MiniCPM5-2BOpenBMB · 2.5B | — | FP16 | 7 Go | +1433 Go | comfortable | Hugging Face ↗ |
| Qwen3 8BAlibaba · 8.2B | — | Q4_K_MFP16 also fits · 20 Go | 7 Go | +1433 Go | comfortable | ollama run qwen3:8b |
| Falcon 3 10BTII · 10.3B | — | Q4_K_MFP16 also fits · 25 Go | 8 Go | +1432 Go | comfortable | ollama run falcon3:10b |
| Granite 4.1 3BIBM · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| Ministral 3 3BMistral AI · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| SmolLM3 3BHugging Face · 3.1B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| Mistral Nemo 12BMistral AI · 12.2B | — | Q4_K_MFP16 also fits · 29 Go | 10 Go | +1430 Go | comfortable | ollama run mistral-nemo |
| Gemma 4 E4BGoogle · 4B | — | FP16 | 11 Go | +1429 Go | comfortable | Hugging Face ↗ |
| Qwen3 14BAlibaba · 14.8B | — | Q4_K_MFP16 also fits · 35 Go | 11 Go | +1429 Go | comfortable | ollama run qwen3:14b |
| DeepSeek-Coder-V2 LiteDeepSeek · 15.7B | — | Q4_K_MFP16 also fits · 37 Go | 12 Go | +1428 Go | comfortable | ollama run deepseek-coder-v2:16b |
| StarCoder 2BigCode · 16B | — | Q4_K_MFP16 also fits · 37 Go | 12 Go | +1428 Go | comfortable | ollama run starcoder2:15b |
| Devstral SmallMistral AI · 24B | — | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1423 Go | comfortable | ollama run devstral |
| Lucie 7BOpenLLM France · 6.7B | — | FP16 | 17 Go | +1423 Go | comfortable | Hugging Face ↗ |
| Magistral SmallMistral AI · 24B | — | Q4_K_MFP16 also fits · 55 Go | 17 Go | +1423 Go | comfortable | ollama run magistral |
| OLMo 3 7BAllen AI · 7B | — | FP16 | 17 Go | +1423 Go | comfortable | Hugging Face ↗ |
| Apertus 8BSwiss AI · 8B | — | FP16 | 20 Go | +1420 Go | comfortable | Hugging Face ↗ |
| Ministral 3 8BMistral AI · 8B | — | FP16 | 20 Go | +1420 Go | comfortable | Hugging Face ↗ |
| InternLM3 8BShanghai AI Lab · 8.8B | — | FP16 | 21 Go | +1419 Go | comfortable | Hugging Face ↗ |
| Apertus 1.5 8BSwiss AI Initiative · 9B | — | FP16 | 22 Go | +1418 Go | comfortable | Hugging Face ↗ |
| EuroLLM 9BUTTER Project · 9.15B | — | FP16 | 22 Go | +1418 Go | comfortable | Hugging Face ↗ |
| DeepSeek-R1 Distill 32BDeepSeek · 32.8B | — | Q4_K_MFP16 also fits · 74 Go | 23 Go | +1417 Go | comfortable | ollama run deepseek-r1:32b |
| Gemma 4 12BGoogle · 12B | — | FP16 | 28 Go | +1412 Go | comfortable | Hugging Face ↗ |
| Ministral 3 14BMistral AI · 14B | — | FP16 | 33 Go | +1407 Go | comfortable | Hugging Face ↗ |
| Qwen3.6 27BAlibaba · 27B | — | FP16 | 61 Go | +1379 Go | comfortable | Hugging Face ↗ |
| Qwen3.6 35B-A3BAlibaba · 35B | — | FP16 | 79 Go | +1361 Go | comfortable | Hugging Face ↗ |
| Apertus 1.5 70BSwiss AI Initiative · 70B | — | FP16 | 156 Go | +1284 Go | comfortable | Hugging Face ↗ |
| Kolibri 1Aleph Alpha · 78.1B | — | FP16 | 174 Go | +1266 Go | comfortable | Hugging Face ↗ |
| Mistral Small 4Mistral AI · 119B | — | FP16 | 264 Go | +1176 Go | comfortable | Hugging Face ↗ |
| Kimi K2.7 CodeMoonshot AI · 1000B | — | Q8_0 | 1179 Go | +261 Go | tight | 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 | +1438 Go | comfortable | Hugging Face ↗ |
| ChatterboxResemble AI · 0.5B | — | FP16 | 3 Go | +1437 Go | comfortable | Hugging Face ↗ |
| Parakeet TDT 0.6B v3NVIDIA · 0.6B | — | FP16 | 3 Go | +1437 Go | comfortable | Hugging Face ↗ |
| TripoSRStability AI · 0.5B | — | FP16 | 3 Go | +1437 Go | comfortable | Hugging Face ↗ |
| Stable Fast 3DStability AI · 1B | — | FP16 | 4 Go | +1436 Go | comfortable | Hugging Face ↗ |
| TRELLISMicrosoft · 1.2B | — | FP16 | 5 Go | +1435 Go | comfortable | Hugging Face ↗ |
| Whisper large-v3OpenAI · 1.55B | — | FP16 | 5 Go | +1435 Go | comfortable | Hugging Face ↗ |
| Dia 1.6BNari Labs · 1.6B | — | FP16 | 6 Go | +1434 Go | comfortable | Hugging Face ↗ |
| Hunyuan3D 2.1Tencent · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| Orpheus 3BCanopy Labs · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| Voxtral Mini 3BMistral AI · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| YuE2-3Bm-a-p (Multimodal Art Projection) · 3B | — | FP16 | 9 Go | +1431 Go | comfortable | Hugging Face ↗ |
| FLUX.2 [klein] 4BBlack Forest Labs · 4B | — | FP16 | 11 Go | +1429 Go | comfortable | Hugging Face ↗ |
| TRELLIS.2Microsoft · 4B | — | FP16 | 11 Go | +1429 Go | comfortable | Hugging Face ↗ |
| CogVideoX 5BZhipu AI · 5B | — | FP16 | 13 Go | +1427 Go | comfortable | Hugging Face ↗ |
| Wan 2.2 5BAlibaba · 5B | — | FP16 | 13 Go | +1427 Go | comfortable | Hugging Face ↗ |
| Ming-Image 0.1 DesignAnt Group · 6B | — | FP16 | 15 Go | +1425 Go | comfortable | Hugging Face ↗ |
| NitroFusion2SketchX (University of Surrey) · 6B | — | FP16 | 15 Go | +1425 Go | comfortable | Hugging Face ↗ |
| Z-Image TurboAlibaba · 6B | — | FP16 | 15 Go | +1425 Go | comfortable | Hugging Face ↗ |
| HunyuanVideo 1.5Tencent · 8.3B | — | FP16 | 20 Go | +1420 Go | comfortable | Hugging Face ↗ |
| GLM-ImageZhipu AI · 9B | — | FP16 | 22 Go | +1418 Go | comfortable | Hugging Face ↗ |
| Mochi 1Genmo · 10B | — | FP16 | 24 Go | +1416 Go | comfortable | Hugging Face ↗ |
| FLUX.1 [dev]Black Forest Labs · 12B | — | FP16 | 28 Go | +1412 Go | comfortable | Hugging Face ↗ |
| HiDream-I1HiDream · 17B | — | FP16 | 39 Go | +1401 Go | comfortable | Hugging Face ↗ |
| Qwen-Image 2512Alibaba · 20B | — | FP16 | 46 Go | +1394 Go | comfortable | Hugging Face ↗ |
| LTX-2.3Lightricks · 22B | — | FP16 | 50 Go | +1390 Go | comfortable | Hugging Face ↗ |
| Voxtral Small 24BMistral AI · 24B | — | FP16 | 55 Go | +1385 Go | comfortable | Hugging Face ↗ |
| Wan 2.2 A14BAlibaba · 27B | — | FP16 | 61 Go | +1379 Go | comfortable | Hugging Face ↗ |
| FLUX.2 [dev]Black Forest Labs · 32B | — | FP16 | 72 Go | +1368 Go | comfortable | Hugging Face ↗ |
| HunyuanImage 3.0Tencent · 80B | — | FP16 | 178 Go | +1262 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.