Catalog
Models 97
2026 releases ranked by the Artificial Analysis Intelligence Index (best evaluated mode). Arena ratings are a separate crowd signal, never blended. File sizes are actual Hugging Face bytes; “—” means no verified file.
Intelligence
Artificial Analysis Intelligence Index · top 15 ranked 2026 open-weight models · higher is better
AA estimate
| Model | Quality | GGUF file size | MLX file size | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| # | Model | Released | Size | AA index | Arena | Q4_K_M | Q5_K_M | Q8_0 | 4-bit | 8-bit |
| 1 | MiMo-V2.6-Pro-MOPD XiaomiMiMo/MiMo-V2.6-Pro-MOPD | 2026-09-27 | 1.02T · 42B active | 46.3 | 1,491 | — | — | — | — | — |
| 2 | GLM-5.3 zai-org/GLM-5.3 | 2026-08-28 | MoE · size unknown | 44.8 | 1,471 | — | — | 746 GiB | — | — |
| 3 | Step 5 Preview stepfun-ai/Step-5-Preview | 2026-10 (day unknown) | 600B · 27B active | 43.7 | 1,441 | — | — | — | — | — |
| 4 | Kimi K3 moonshotai/Kimi-K3 | 2026-07-27 | 2.8T · 104B active | 43.6 | 1,475 | — | — | — | — | — |
| 5 | GLM-5.3-Flash zai-org/GLM-5.3-Flash | 2026-08-26 | 320B · 18B active | 41.8 | 1,471 | — | — | 318 GiB | 190 GiB | 311 GiB |
| 6 | Ling 3.1 Flash inclusionAI/Ling-3.1-flash | 2026 (month unknown) | 560B · 25B active | 41.1 | — | 333 GiB | 406 GiB | 567 GiB | — | — |
| 7 | Qwen3.8-2.4T-A95B Qwen/Qwen3.8-2.4T-A95B | 2026-08-12 | 2.4T · 95B active | 39.9 | — | — | — | 2,422 GiB | — | — |
| 8 | Qwen3.8-Flash-Next Qwen/Qwen3.8-Flash-Next | 2026-08-26 | 180B · 6B active | 39.8 | — | — | — | 175 GiB | 104 GiB | — |
| 9 | DeepSeek V4.1 Flash deepseek-ai/DeepSeek-V4.1-Flash | 2026-09-10 | 552B · 16B active | 39.5 | 1,463 | — | — | — | — | — |
| 10 | Muse Spark Open (816B-A42B) meta-models/Muse-Spark-Open-816B-A42B | 2026-10-15 | 816B · 42B active | 38.9 | — | — | — | 812 GiB | 496 GiB | — |
| 11 | MiMo-V2.6-Flash-MOPD XiaomiMiMo/MiMo-V2.6-Flash-MOPD | 2026-09-27 | 309B · 15B active | 37.9 | 1,455 | — | — | — | — | — |
| 12 | DeepSeek V4 Pro 0813 deepseek-ai/DeepSeek-V4-Pro-0813 | 2026-08-13 | MoE · size unknown | 36.0 | 1,446 | — | — | — | — | — |
| 13 | Qwen3.8-27B Qwen/Qwen3.8-27B | 2026-08-14 | 27B dense | 33.7 | 1,441 | 16.2 GiB | 19.5 GiB | 27.1 GiB | 15.0 GiB | 27.5 GiB |
| 14 | Motif 3 Motif-Technologies/Motif-3 | 2026-08 (day unknown) | 314B · 13B active | 33.6 AA estimate | — | 183 GiB | 220 GiB | — | — | 312 GiB |
| 15 | K2-Horizon-375B-A23B IFM/K2-Horizon-375B-A23B | 2026-09-03 | 375B · 23B active | 30.5 | — | 221 GiB | 270 GiB | 375 GiB | — | — |
| 16 | Reflection Beam 1.0 501B-A23B reflection/Beam-1.0-501B-A23B | 2026-10-16 | 501B · 23B active | 30.3 | — | — | — | 496 GiB | — | — |
| 17 | MiniMax-M3 MiniMaxAI/MiniMax-M3 | 2026-06 (day unknown) | 428B · 23B active | 29.2 | 1,433 | 243 GiB | 284 GiB | 422 GiB | 225 GiB | 421 GiB |
| 18 | Nex-N2-Pro (Qwen3.5-397B-A17B based) nex-agi/Nex-N2-Pro | 2026-06 (day unknown) | 397B · 17B active | 28.2 AA estimate | — | 225 GiB | 264 GiB | 393 GiB | — | 392 GiB |
| 19 | NVIDIA Nemotron 3.5 Super VL 120B-A12B nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 | 2026-10-15 | 120B · 12B active | 26.5 | 1,409 | — | — | 123 GiB | 64.6 GiB | — |
| 20 | Kimi K2.7 Code moonshotai/Kimi-K2.7-Code | 2026-06-12 | 1T · 32B active | 25.8 | — | 578 GiB | — | — | 597 GiB | — |
| 21 | Inkling-Small thinkingmachines/Inkling-Small | 2026-07-30 | 276B · 12B active | 25.7 | 1,413 | — | — | 261 GiB | 143 GiB | — |
| 22 | K2-Horizon-MoVA-36B-A4B IFM/K2-Horizon-MoVA-36B-A4B | 2026-09-03 | 36B · 4B active | 25.3 | — | 20.8 GiB | 24.6 GiB | 37.1 GiB | 24.6 GiB | 37.1 GiB |
| 23 | Hy3 tencent/Hy3 | 2026-07-06 | 295B · 21B active | 25.3 | 1,438 | 170 GiB | — | — | — | — |
| 24 | Inkling thinkingmachines/Inkling | 2026-07-15 | 975B · 41B active | 25.0 | 1,441 | — | — | 798 GiB | 511 GiB | — |
| 25 | Solar Open 2 (250B-A15B) upstage/Solar-Open2-250B | 2026-07-22 | 250B · 15B active | 24.7 AA estimate | — | — | — | 248 GiB | 131 GiB | 248 GiB |
| 26 | Ling-3.0-flash-VL inclusionAI/Ling-3.0-flash-VL | 2026-09-09 | 124B · 5.5B active | 24.6 | — | 73.3 GiB | 89.3 GiB | 123 GiB | — | — |
| 27 | NVIDIA Nemotron 3 Ultra 550B-A55B nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 2026-06-04 | 550B · 55B active | 22.9 | 1,445 | 321 GiB | 369 GiB | 544 GiB | 288 GiB | 544 GiB |
| 28 | Ling-3.0-flash-Fin inclusionAI/Ling-3.0-flash-Fin | 2026 (month unknown) | 124B · 5.1B active | 22.6 | — | 72.5 GiB | 84.4 GiB | 126 GiB | — | — |
| 29 | G9v3-39A5B (preview) ai9stars/G9v3-39A5B | 2026-08 (day unknown) | 39B · 5B active | 21.8 AA estimate | — | 21.9 GiB | — | 38.6 GiB | 21.2 GiB | — |
| 30 | A.X K2 (SK Telecom) skt/A.X-K2 | 2026-07-29 | 688B · 33B active | 21.5 | — | — | — | — | — | — |
| 31 | Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B | 2026-02-16 | 397B · 17B active | 21.4 AA estimate | 1,438 | 227 GiB | 273 GiB | 393 GiB | 208 GiB | 393 GiB |
| 32 | NVIDIA Nemotron 3.5 Bolt 74B-A9B nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 | 2026-10-15 | 74B · 9B active | 21.4 | — | — | — | 73.4 GiB | 40.3 GiB | 74.7 GiB |
| 33 | K2-Horizon-7B IFM/K2-Horizon-7B | 2026-09-03 | size unknown | 20.6 | — | 5.2 GiB | 6.0 GiB | 8.9 GiB | 6.7 GiB | 8.9 GiB |
| 34 | K-EXAONE 2.0 750B-A37B LGAI-EXAONE/K-EXAONE-2.0-750B-A37B | 2026-07-31 | 750B · 37B active | 19.7 AA estimate | — | — | — | — | — | — |
| 35 | LongCat-2.0 meituan-longcat/LongCat-2.0 | 2026-07 (day unknown) | 1.6T · 48B active | 19.1 | — | — | — | — | — | — |
| 36 | Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B | 2026-04-16 | 35B · 3B active | 18.2 | — | 19.0 GiB | 23.0 GiB | 34.4 GiB | 19.0 GiB | 35.1 GiB |
| 37 | Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B | 2026-02-24 | 122B · 10B active | 17.7 AA estimate | 1,417 | 71.3 GiB | 85.2 GiB | 121 GiB | 64.8 GiB | 122 GiB |
| 38 | Muse Glimmer 30B meta-models/Muse-Glimmer-30B | 2026-08-10 | 30B dense | 17.5 | 1,389 | 15.6 GiB | 18.7 GiB | 27.6 GiB | 18.1 GiB | 31.1 GiB |
| 39 | Gemma 4 26B A4B (it) google/gemma-4-26B-A4B-it | 2026-04-02 | 25B · 3.8B active | 16.7 AA estimate | 1,434 | 15.6 GiB | — | 25.0 GiB | 14.3 GiB | 26.0 GiB |
| 40 | Ring-2.6-1T inclusionAI/Ring-2.6-1T | 2026-05-15 | 1T · 63B active | 16.6 | — | — | — | — | — | — |
| 41 | K2-Horizon-3.7B IFM/K2-Horizon-3.7B | 2026-09-03 | size unknown | 15.6 | — | 2.9 GiB | 3.4 GiB | 5.0 GiB | 3.9 GiB | 5.0 GiB |
| 42 | Gemma 4 31B (it) google/gemma-4-31B-it | 2026-04-02 | 31B dense | 14.7 | 1,443 | 17.1 GiB | 20.2 GiB | 30.4 GiB | 17.1 GiB | 31.4 GiB |
| 43 | Mistral Medium 3.5 (128B dense) mistralai/Mistral-Medium-3.5-128B | 2026-04-28 | 128B dense | 14.2 | 1,421 | 69.8 GiB | 82.3 GiB | 124 GiB | 72.6 GiB | — |
| 44 | Gemma 4 12B (it) google/gemma-4-12B-it | 2026-06-03 | 12B dense | 14.2 AA estimate | — | 7.1 GiB | 8.2 GiB | 11.8 GiB | 6.3 GiB | 11.8 GiB |
| 45 | Qwen3.5-9B Qwen/Qwen3.5-9B | 2026-03-02 | 9B dense | 13.3 AA estimate | — | 5.3 GiB | 6.1 GiB | 8.9 GiB | 5.5 GiB | 9.7 GiB |
| 46 | EXAONE 4.5 33B LGAI-EXAONE/EXAONE-4.5-33B | 2026-04-09 | 33B dense | 13.2 AA estimate | — | 18.7 GiB | 21.9 GiB | 32.7 GiB | — | — |
| 47 | Command A+ (05-2026) CohereLabs/command-a-plus-05-2026-bf16 | 2026-05-20 | 218B · 25B active | 13.1 | — | 123 GiB | 144 GiB | 216 GiB | — | — |
| 48 | Qwen3.5-4B Qwen/Qwen3.5-4B | 2026-03-02 | 4B dense | 13.1 AA estimate | — | 2.6 GiB | 2.9 GiB | 4.2 GiB | 2.8 GiB | 4.8 GiB |
| 49 | NVIDIA Nemotron 3.5 Lightning 30B-A3B nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 2026-08-11 | 30B · 3B active | 12.9 | 1,329 | 23.7 GiB | 25.1 GiB | 32.6 GiB | 16.6 GiB | 31.3 GiB |
| 50 | IBM Granite 4.2 30B ibm-granite/granite-4.2-30b | 2026-08-25 | 30B dense | 12.7 | 1,361 | 16.5 GiB | 19.3 GiB | 29.0 GiB | 15.3 GiB | 29.0 GiB |
| 51 | MiniCPM5-2B openbmb/MiniCPM5-2B | 2026-09-07 | 2.5B dense | 12.5 | — | 1.5 GiB | 1.8 GiB | 2.5 GiB | 1.3 GiB | 2.5 GiB |
| 52 | HyperNova 60B 2605 (compressed gpt-oss-120b) MultiverseComputingCAI/Hypernova-60B-2605 | 2026-05-06 | 60B · 4.8B active | 11.7 AA estimate | — | 37.9 GiB | 41.3 GiB | 58.1 GiB | — | — |
| 53 | Nemotron Cascade 2 30B A3B nvidia/Nemotron-Cascade-2-30B-A3B | 2026-03-19 | 30B · 3B active | 11.7 AA estimate | — | 22.8 GiB | 24.3 GiB | 31.3 GiB | 16.6 GiB | 31.3 GiB |
| 54 | LongCat-Flash-Lite meituan-longcat/LongCat-Flash-Lite | 2026-01 (day unknown) | 69B · 3B active | 11.5 AA estimate | — | 37.5 GiB | 44.7 GiB | 67.9 GiB | 35.9 GiB | 67.8 GiB |
| 55 | Mistral Small 4 (119B-2603) mistralai/Mistral-Small-4-119B-2603 | 2026-03-16 | 119B · 6B active | 11.3 | — | 67.6 GiB | 79.2 GiB | 118 GiB | — | — |
| 56 | Granite 4.2 8B ibm-granite/granite-4.2-8b | 2026-08-25 | 8B dense | 11.1 | 1,320 | 5.0 GiB | 5.8 GiB | 8.7 GiB | 4.6 GiB | 8.7 GiB |
| 57 | Ling-3.0-tiny inclusionAI/Ling-3.0-tiny | 2026-08 (day unknown) | 7.9B · 1.3B active | 11.1 | — | 4.5 GiB | 5.2 GiB | 7.8 GiB | 4.1 GiB | — |
| 58 | G9v3-3B AI9Stars/G9v3-3B | 2026-07 (day unknown) | 3B dense | 10.8 AA estimate | — | 1.7 GiB | 2.0 GiB | 3.0 GiB | 1.6 GiB | — |
| 59 | Trinity-Large-Thinking arcee-ai/Trinity-Large-Thinking | 2026-04-01 | 398B · 13B active | 10.8 | — | 225 GiB | 264 GiB | 395 GiB | 209 GiB | 394 GiB |
| 60 | Nemotron 3 Nano Omni 30B A3B Reasoning nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | 2026-04-28 | 30B · 3B active | 10.3 AA estimate | — | 22.8 GiB | — | 31.3 GiB | 18.3 GiB | 33.3 GiB |
| 61 | North Mini Code CohereLabs/North-Mini-Code-1.0 | 2026-06-09 | 30B · 3B active | 9.9 | — | 17.5 GiB | 20.3 GiB | 30.2 GiB | 17.2 GiB | 31.0 GiB |
| 62 | DiffusionGemma 26B A4B google/diffusiongemma-26B-A4B-it | 2026-06-10 | 25B · 3.8B active | 9.5 AA estimate | — | 15.7 GiB | 17.8 GiB | 25.0 GiB | 15.4 GiB | 26.1 GiB |
| 63 | Qwen3-Coder-Next Qwen/Qwen3-Coder-Next | 2026-02-02 | 80B · 3B active | 9.2 | — | 45.2 GiB | 52.9 GiB | 79.0 GiB | 41.8 GiB | 78.8 GiB |
| 64 | Granite 4.2 3B ibm-granite/granite-4.2-3b | 2026-08-25 | 3B dense | 9.1 | 1,293 | 2.1 GiB | 2.4 GiB | 3.6 GiB | 1.9 GiB | 3.6 GiB |
| 65 | Tri-21B-Think trillionlabs/Tri-21B-Think | 2026-02 (day unknown) | 21B dense | 9.0 AA estimate | — | 11.7 GiB | 13.7 GiB | 20.5 GiB | — | — |
| 66 | Gemma 4 E4B (it) google/gemma-4-E4B-it | 2026-04-02 | 8B dense | 8.9 | — | 4.6 GiB | 5.1 GiB | 7.6 GiB | 4.8 GiB | 8.3 GiB |
| 67 | MiniCPM5-1B openbmb/MiniCPM5-1B | 2026-05-19 | 1.1B dense | 8.8 AA estimate | — | 0.6 GiB | 0.7 GiB | 1.1 GiB | 0.6 GiB | 1.1 GiB |
| 68 | Sarvam 105B sarvamai/sarvam-105b | 2026-03-06 | 105B · 10B active | 8.8 AA estimate | — | 59.8 GiB | — | 105 GiB | — | — |
| 69 | Nanbeige4.1-3B Nanbeige/Nanbeige4.1-3B | 2026-02 (day unknown) | 3B dense | 8.4 AA estimate | — | 2.3 GiB | 2.6 GiB | 3.9 GiB | 2.1 GiB | 3.9 GiB |
| 70 | LFM2.5-2.6B LiquidAI/LFM2.5-2.6B | 2026-08-04 | 2.7B dense | 8.4 AA estimate | — | 1.6 GiB | 1.8 GiB | 2.7 GiB | 1.5 GiB | 2.7 GiB |
| 71 | Falcon-H1R-7B tiiuae/Falcon-H1R-7B | 2026-01-05 | 7B dense | 7.8 AA estimate | — | 4.3 GiB | 5.0 GiB | 7.5 GiB | 4.0 GiB | 7.5 GiB |
| 72 | Gemma 4 E2B google/gemma-4-E2B-it | 2026-04-02 | 5.1B dense | 7.8 AA estimate | — | 2.9 GiB | 3.1 GiB | 4.7 GiB | 3.3 GiB | 5.5 GiB |
| 73 | Step3 VL 10B stepfun-ai/Step3-VL-10B | 2026-01 (day unknown) | 10B dense | 7.7 AA estimate | — | 4.7 GiB | 5.4 GiB | 8.1 GiB | — | — |
| 74 | LFM2.5-8B-A1B LiquidAI/LFM2.5-8B-A1B | 2026-05-28 | 8.3B · 1.5B active | 7.2 AA estimate | — | 4.8 GiB | 5.6 GiB | 8.4 GiB | 4.5 GiB | 8.4 GiB |
| 75 | NVIDIA Nemotron 3 Nano 4B nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 | 2026-03-16 | 4B dense | 4.8 | — | 2.6 GiB | 2.9 GiB | 3.9 GiB | 2.1 GiB | 3.9 GiB |
| — | LFM2.5-24B-A2B LiquidAI/LFM2.5-24B-A2B | 2026-10-13 | 24B · 2B active | — | — | 13.5 GiB | 15.9 GiB | 23.7 GiB | 12.6 GiB | 23.7 GiB |
| — | MiniCPM-V 4.7 35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B | 2026-10-12 | 35B · 3B active | — | — | 19.7 GiB | 23.0 GiB | 34.4 GiB | 21.9 GiB | 37.1 GiB |
| — | Mellum2.1-12B-A2.5B-Thinking JetBrains/Mellum2.1-12B-A2.5B-Thinking | 2026-10-08 | 12B · 2.5B active | — | — | 7.5 GiB | 9.3 GiB | 12.0 GiB | — | — |
| — | Aleph Alpha Kolibri-1 Aleph-Alpha/Kolibri-1 | 2026-10-03 | 78B · 3.5B active | — | — | 44.2 GiB | 51.8 GiB | 77.4 GiB | 41.3 GiB | — |
| — | MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B | 2026-09-22 | 9B dense | — | — | 5.4 GiB | 6.4 GiB | 8.9 GiB | 5.5 GiB | 9.7 GiB |
| — | K2-Horizon-0.9B IFM/K2-Horizon-0.9B | 2026-09-03 | size unknown | — | — | 0.6 GiB | 0.7 GiB | 1.1 GiB | 0.8 GiB | 1.1 GiB |
| — | Hy4-preview tencent/Hy4-preview | 2026-08-28 | 770B · 49B active | — | — | 435 GiB | — | — | 404 GiB | — |
| — | Ling-3.0-flash inclusionAI/Ling-3.0-flash | 2026-08-07 | 124B · 5.1B active | — | — | 72.5 GiB | 84.4 GiB | 126 GiB | 65.2 GiB | 123 GiB |
| — | Ornith-1.5-9B ornith-ai/Ornith-1.5-9B | 2026-08 (day unknown) | 9B dense | — | — | 5.4 GiB | 6.2 GiB | 9.1 GiB | 4.7 GiB | 8.9 GiB |
| — | DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-0731 | 2026-07-31 | MoE · size unknown | — | — | — | — | — | 144 GiB | — |
| — | Poolside Laguna S 2.1 poolside/Laguna-S-2.1 | 2026-07-21 | 118B · 8B active | — | — | 89.4 GiB | — | 120 GiB | 61.6 GiB | 116 GiB |
| — | GLM-5.2 zai-org/GLM-5.2 | 2026-06-16 | MoE · size unknown | — | — | — | — | 746 GiB | 390 GiB | 736 GiB |
| — | Step 3.7 Flash stepfun-ai/Step-3.7-Flash | 2026-05-29 | 198B · 11B active | — | — | — | — | 195 GiB | 103 GiB | 195 GiB |
| — | Qwen3.6-27B Qwen/Qwen3.6-27B | 2026-04-22 | 27B dense | — | — | 15.7 GiB | 18.2 GiB | 26.6 GiB | 15.0 GiB | 27.5 GiB |
| — | Kimi K2.6 moonshotai/Kimi-K2.6 | 2026-04-20 | 1T · 32B active | — | — | — | — | — | 612 GiB | — |
| — | NVIDIA Nemotron 3 Super 120B-A12B nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 2026-03-11 | 120B · 12B active | — | — | — | — | 120 GiB | 63.3 GiB | 119 GiB |
| — | Qwen3.5-0.8B Qwen/Qwen3.5-0.8B | 2026-03-02 | 0.8B dense | — | — | 0.5 GiB | 0.5 GiB | 0.8 GiB | 0.6 GiB | 0.9 GiB |
| — | Qwen3.5-2B Qwen/Qwen3.5-2B | 2026-03-02 | 2B dense | — | — | 1.2 GiB | 1.3 GiB | 1.9 GiB | 1.6 GiB | 2.5 GiB |
| — | Qwen3.5-27B Qwen/Qwen3.5-27B | 2026-02-24 | 27B dense | — | — | 15.6 GiB | 18.3 GiB | 26.6 GiB | 15.0 GiB | 27.5 GiB |
| — | Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B | 2026-02-24 | 35B · 3B active | — | — | 20.5 GiB | 24.4 GiB | 34.4 GiB | 19.0 GiB | 35.1 GiB |
| — | GLM-4.7-Flash zai-org/GLM-4.7-Flash | 2026-01 (day unknown) | 30B · 3B active | — | — | 17.1 GiB | 19.9 GiB | 29.7 GiB | 15.7 GiB | 29.6 GiB |
| — | MiniMax-M2.7 MiniMaxAI/MiniMax-M2.7 | 2026 (month unknown) | MoE · size unknown | — | — | 129 GiB | 151 GiB | 226 GiB | 120 GiB | 226 GiB |
| — | MiMo-V2.6-Flash Superseded XiaomiMiMo/MiMo-V2.6-Flash-RL | 2026-09-22 | 309B · 15B active | 37.9 | 1,455 | — | — | — | 157 GiB | — |
| — | MiMo-V2.6-Pro Superseded XiaomiMiMo/MiMo-V2.6-Pro-RL | 2026-09-22 | 1.02T · 42B active | 46.3 | 1,491 | — | — | — | — | — |
| — | Nanbeige4.2-3B Date unverified Nanbeige/Nanbeige4.2-3B | Release date unknown | 4B dense | — | — | 2.4 GiB | 2.8 GiB | 4.1 GiB | 2.2 GiB | 4.1 GiB |
| — | Qwen3-Next-80B-A3B-Instruct Legacy Qwen/Qwen3-Next-80B-A3B-Instruct | 2025-09-11 | 81B · 3B active | — | — | — | — | — | — | — |
| — | gpt-oss-20b Legacy openai/gpt-oss-20b | 2025-08-05 | 21B · 3.6B active | — | — | — | — | — | — | — |
| — | gpt-oss-120b Legacy openai/gpt-oss-120b | 2025-08-05 | 117B · 5.1B active | — | — | — | — | — | — | — |
| — | Qwen3-Coder-30B-A3B-Instruct Legacy Qwen/Qwen3-Coder-30B-A3B-Instruct | 2025-07-31 | 31B · 3.3B active | — | — | — | — | — | — | — |
| — | GLM-4.5-Air Legacy zai-org/GLM-4.5-Air | 2025-07-28 | 110B · 12B active | — | — | — | — | — | — | — |
| — | Qwen3-Coder-480B-A35B-Instruct Legacy Qwen/Qwen3-Coder-480B-A35B-Instruct | 2025-07-22 | 480B · 35B active | — | — | — | — | — | — | — |
| — | Mistral Small 3.2 24B Instruct (2506) Legacy mistralai/Mistral-Small-3.2-24B-Instruct-2506 | 2025-06-20 | 24B dense | — | — | — | — | — | — | — |
| — | Qwen3-0.6B Legacy Qwen/Qwen3-0.6B | 2025-04-29 | 0.6B dense | — | — | — | — | — | — | — |
| — | Qwen3-1.7B Legacy Qwen/Qwen3-1.7B | 2025-04-29 | 1.7B dense | — | — | — | — | — | — | — |
| — | Qwen3-4B Legacy Qwen/Qwen3-4B | 2025-04-29 | 4B dense | — | — | — | — | — | — | — |
| — | Qwen3-8B Legacy Qwen/Qwen3-8B | 2025-04-29 | 8.2B dense | — | — | — | — | — | — | — |
| — | Qwen3-14B Legacy Qwen/Qwen3-14B | 2025-04-29 | 15B dense | — | — | — | — | — | — | — |
| — | Qwen3-32B Legacy Qwen/Qwen3-32B | 2025-04-29 | 33B dense | — | — | — | — | — | — | — |
| — | Qwen3-30B-A3B Legacy Qwen/Qwen3-30B-A3B | 2025-04-29 | 31B · 3.3B active | — | — | — | — | — | — | — |
| — | Qwen3-235B-A22B Legacy Qwen/Qwen3-235B-A22B | 2025-04-29 | 235B · 22B active | — | — | — | — | — | — | — |
| — | Llama 4 Scout 17B-16E Instruct Legacy meta-llama/Llama-4-Scout-17B-16E-Instruct | 2025-04-05 | 109B · 17B active | — | — | — | — | — | — | — |
| — | Llama 4 Maverick 17B-128E Instruct Legacy meta-llama/Llama-4-Maverick-17B-128E-Instruct | 2025-04-05 | 402B · 17B active | — | — | — | — | — | — | — |
| — | Gemma 3 1B IT Legacy google/gemma-3-1b-it | 2025-03-12 | 1B dense | — | — | — | — | — | — | — |
| — | Gemma 3 4B IT Legacy google/gemma-3-4b-it | 2025-03-12 | 4.3B dense | — | — | — | — | — | — | — |
| — | Gemma 3 12B IT Legacy google/gemma-3-12b-it | 2025-03-12 | 12B dense | — | — | — | — | — | — | — |
| — | Gemma 3 27B IT Legacy google/gemma-3-27b-it | 2025-03-12 | 27B dense | — | — | — | — | — | — | — |
| — | Phi-4-mini-instruct Legacy microsoft/Phi-4-mini-instruct | 2025-02-26 | 3.8B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Qwen-1.5B Legacy deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | 2025-01-20 | 1.8B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Qwen-7B Legacy deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 2025-01-20 | 7.6B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Llama-8B Legacy deepseek-ai/DeepSeek-R1-Distill-Llama-8B | 2025-01-20 | 8B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Qwen-14B Legacy deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 2025-01-20 | 15B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Qwen-32B Legacy deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 2025-01-20 | 33B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1-Distill-Llama-70B Legacy deepseek-ai/DeepSeek-R1-Distill-Llama-70B | 2025-01-20 | 71B dense | — | — | — | — | — | — | — |
| — | DeepSeek-R1 Legacy deepseek-ai/DeepSeek-R1 | 2025-01-20 | 671B · 37B active | — | — | — | — | — | — | — |
| — | DeepSeek-V3 Legacy deepseek-ai/DeepSeek-V3 | 2024-12-26 | 671B · 37B active | — | — | — | — | — | — | — |
| — | Phi-4 Legacy microsoft/phi-4 | 2024-12-12 | 15B dense | — | — | — | — | — | — | — |
| — | Llama 3.3 70B Instruct Legacy meta-llama/Llama-3.3-70B-Instruct | 2024-12-06 | 71B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-Coder-32B-Instruct Legacy Qwen/Qwen2.5-Coder-32B-Instruct | 2024-11-12 | 33B dense | — | — | — | — | — | — | — |
| — | Llama 3.2 1B Instruct Legacy meta-llama/Llama-3.2-1B-Instruct | 2024-09-25 | 1.2B dense | — | — | — | — | — | — | — |
| — | Llama 3.2 3B Instruct Legacy meta-llama/Llama-3.2-3B-Instruct | 2024-09-25 | 3.2B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-7B-Instruct Legacy Qwen/Qwen2.5-7B-Instruct | 2024-09-19 | 7.6B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-14B-Instruct Legacy Qwen/Qwen2.5-14B-Instruct | 2024-09-19 | 15B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-32B-Instruct Legacy Qwen/Qwen2.5-32B-Instruct | 2024-09-19 | 33B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-72B-Instruct Legacy Qwen/Qwen2.5-72B-Instruct | 2024-09-19 | 73B dense | — | — | — | — | — | — | — |
| — | Qwen2.5-Coder-7B-Instruct Legacy Qwen/Qwen2.5-Coder-7B-Instruct | 2024-09-19 | 7.6B dense | — | — | — | — | — | — | — |
| — | Llama 3.1 8B Instruct Legacy meta-llama/Llama-3.1-8B-Instruct | 2024-07-23 | 8B dense | — | — | — | — | — | — | — |
| — | Llama 3.1 70B Instruct Legacy meta-llama/Llama-3.1-70B-Instruct | 2024-07-23 | 71B dense | — | — | — | — | — | — | — |
| — | Mistral NeMo 12B Instruct (2407) Legacy mistralai/Mistral-Nemo-Instruct-2407 | 2024-07-18 | 12B dense | — | — | — | — | — | — | — |
| — | Mistral 7B Instruct v0.3 Legacy mistralai/Mistral-7B-Instruct-v0.3 | 2024-05-22 | 7.2B dense | — | — | — | — | — | — | — |
| — | Mixtral 8x22B Instruct v0.1 Legacy mistralai/Mixtral-8x22B-Instruct-v0.1 | 2024-04-17 | 141B · 39B active | — | — | — | — | — | — | — |
| — | Mixtral 8x7B Instruct v0.1 Legacy mistralai/Mixtral-8x7B-Instruct-v0.1 | 2023-12-11 | 47B · 13B active | — | — | — | — | — | — | — |
| — | Llama 2 7B Legacy meta-llama/Llama-2-7b-hf | 2023-07-18 | 6.7B dense | — | — | — | — | — | — | — |
Click a column to sort; unknown values sort last. AA = Artificial Analysis Intelligence Index of the evaluated hosted variant.