Models
Deduplicated to base models. Quantizations are an attribute, not a separate page.
| Model | Publisher | Params | Quants | Range | Downloads |
|---|---|---|---|---|---|
| Qwen3-Coder-30B-A3B-InstructMoE | Qwen | 30.5B | 46 | 7.46 GiB – 56.90 GiB | 9.9M |
| Qwen3.6-27B | Qwen | 27.8B | 40 | 8.74 GiB – 50.90 GiB | 6.6M |
| Qwen3.8-27B | Qwen | 27.8B | 22 | 8.39 GiB – 55.65 GiB | 2.9M |
| DeepSeek-V4-FlashMoE | deepseek-ai | 291B | 12 | 76.87 GiB – 153.33 GiB | 2.0M |
| gemma-4-12B-it-qat-q4_0-unquantized | 12.0B | 2 | 6.50 GiB – 6.50 GiB | 1.4M | |
| gemma-4-E4B-it | 8.0B | 36 | 3.30 GiB – 14.18 GiB | 1.3M | |
| Qwen3-30B-A3B-Thinking-2507MoE | Qwen | 30.5B | 51 | 7.05 GiB – 56.90 GiB | 1.3M |
| Qwen3-4B | Qwen | 4.0B | 29 | 1.01 GiB – 7.50 GiB | 1.1M |
| Qwen3-8B | Qwen | 8.2B | 51 | 2.12 GiB – 15.26 GiB | 1.0M |
| Laguna-XS-2.1MoE | poolside | 33.4B | 31 | 8.76 GiB – 62.33 GiB | 863k |
| HyperCLOVAX-SEED-Text-Instruct-1.5B | naver-hyperclovax | 1.6B | 1 | 1.06 GiB – 1.06 GiB | 833k |
| DeepSeek-V4-Flash-0731MoE | deepseek-ai | 304B | 11 | 76.87 GiB – 145.64 GiB | 814k |
| Llama-3.2-1B-Instruct | meta-llama | 1.2B | 39 | 0.39 GiB – 2.31 GiB | 779k |
| Qwen-AgentWorld-35B-A3BMoE | Qwen | 34.7B | 15 | 10.71 GiB – 66.19 GiB | 775k |
| gpt-oss-20bMoE | openai | 21.5B | 15 | 10.68 GiB – 12.85 GiB | 762k |
| KAT-Coder-V2.5-DevMoE | Kwaipilot | 34.7B | 29 | 9.11 GiB – 64.61 GiB | 760k |
| Qwen3-30B-A3BMoE | Qwen | 30.5B | 51 | 7.59 GiB – 56.90 GiB | 703k |
| llama-3-youko-8b | rinna | 8.0B | 2 | 5.34 GiB – 7.95 GiB | 690k |
| Laguna-S-2.1MoE | poolside | 118B | 49 | 23.15 GiB – 219.05 GiB | 672k |
| Qwen3-VL-8B-Instruct-abliterated-v1 | prithivMLmods | 8.8B | 48 | 1.97 GiB – 15.26 GiB | 640k |
| Llama-3.1-8B-Instruct | meta-llama | 8.0B | 45 | 2.02 GiB – 29.92 GiB | 627k |
| ced-base | mispeech | 86M | 3 | 0.12 GiB – 0.32 GiB | 608k |
| Hy3MoE | tencent | 299B | 37 | 59.65 GiB – 295.84 GiB | 604k |
| Qwen2.5-7B-Instruct | Qwen | 7.6B | 32 | 2.59 GiB – 14.19 GiB | 580k |
| UI-TARS-1.5-7B | ByteDance-Seed | 8.3B | 14 | 2.81 GiB – 14.19 GiB | 555k |
| gemma-3-1b-it | 1000M | 28 | 0.52 GiB – 1.87 GiB | 554k | |
| gemma-4-E2B-it-qat-q4_0-unquantized | 5.1B | 3 | 3.12 GiB – 8.80 GiB | 553k | |
| Qwen3-1.7B | Qwen | 2.0B | 48 | 0.50 GiB – 3.79 GiB | 541k |
| GLM-4.7-FlashMoE | zai-org | 31.2B | 26 | 7.76 GiB – 55.79 GiB | 541k |
| embeddinggemma-300m | 303M | 10 | 0.26 GiB – 1.13 GiB | 535k | |
| Llama-3.2-3B-Instruct | meta-llama | 3.2B | 39 | 0.85 GiB – 5.99 GiB | 533k |
| Qwen3-0.6B | Qwen | 752M | 44 | 0.20 GiB – 1.41 GiB | 527k |
| GLM-5.2MoE | zai-org | 753B | 20 | 169.33 GiB – 1404.42 GiB | 516k |
| Qwen3-14B | Qwen | 14.8B | 29 | 3.56 GiB – 27.51 GiB | 504k |
| Ornith-1.0-35BMoE | deepreinforce-ai | 34.7B | 43 | 9.11 GiB – 66.19 GiB | 491k |
| Wan2.1-T2V-1.3B | Wan-AI | 1.4B | 31 | 0.61 GiB – 11.37 GiB | 399k |
| Qwen3-Coder-NextMoE | Qwen | 79.7B | 61 | 15.44 GiB – 148.51 GiB | 382k |
| Bielik-11B-v3.0-Instruct | speakleash | 11.2B | 6 | 6.26 GiB – 20.80 GiB | 378k |
| LFM2.5-1.2B-Instruct | LiquidAI | 1.2B | 23 | 0.45 GiB – 2.18 GiB | 376k |
| Qwen2.5-Coder-7B-Instruct | Qwen | 7.6B | 32 | 2.59 GiB – 15.08 GiB | 353k |
| Qwen2.5-32B-Instruct | Qwen | 32.8B | 35 | 8.41 GiB – 61.04 GiB | 353k |
| Qwen2.5-1.5B-Instruct | Qwen | 1.5B | 32 | 0.56 GiB – 2.88 GiB | 329k |
| Jan-v3-4B-base-instruct | janhq | 4.4B | 49 | 1.56 GiB – 8.22 GiB | 315k |
| gemma-3-4b-it | 4.3B | 28 | 1.43 GiB – 7.23 GiB | 313k | |
| MiniCPM5-1B-Claude-Opus-Fable5-Thinking | GnLOLot | 1.1B | 15 | 0.43 GiB – 2.02 GiB | 306k |
| Ornith-1.0-9B | deepreinforce-ai | 9.2B | 48 | 2.26 GiB – 17.14 GiB | 291k |
| Agents-A1MoE | InternScience | 35.1B | 3 | 19.71 GiB – 64.61 GiB | 273k |
| gemma-4-26B-A4B-it-ultra-uncensored-hereticMoE | llmfan46 | 25.8B | 43 | 7.72 GiB – 47.04 GiB | 270k |
| Qwen2.5-Coder-32B-Instruct | Qwen | 32.8B | 36 | 8.41 GiB – 64.86 GiB | 269k |
| Qwen2.5-Coder-14B-Instruct | Qwen | 14.8B | 35 | 4.38 GiB – 29.25 GiB | 259k |
| Qwen3-4B-Instruct-2507 | Qwen | 4.0B | 47 | 1.01 GiB – 7.50 GiB | 251k |
| granite-4.1-3b | ibm-granite | 3.4B | 30 | 1.20 GiB – 6.34 GiB | 250k |
| Qwen2.5-3B-Instruct | Qwen | 3.1B | 33 | 1.06 GiB – 11.50 GiB | 240k |
| Phi-3.5-mini-instruct | microsoft | 3.8B | 36 | 0.78 GiB – 14.24 GiB | 238k |
| gemma-2-2b-it | 2.6B | 34 | 0.78 GiB – 9.74 GiB | 232k | |
| Qwen3-30B-A3B-Instruct-2507MoE | Qwen | 30.5B | 51 | 7.05 GiB – 56.90 GiB | 228k |
| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | GnLOLot | 1.1B | 10 | 0.64 GiB – 2.02 GiB | 226k |
| Qwen2.5-0.5B-Instruct | Qwen | 494M | 32 | 0.31 GiB – 0.93 GiB | 224k |
| DeepSeek-R1-0528-Qwen3-8B | deepseek-ai | 8.2B | 47 | 2.11 GiB – 15.26 GiB | 222k |
| Qwen3-32B | Qwen | 32.8B | 29 | 7.21 GiB – 61.03 GiB | 210k |
| Qwen3-VL-8B-Instruct | Qwen | 8.8B | 26 | 2.13 GiB – 15.26 GiB | 185k |
| Sugoi-14B-Ultra-HF | sugoitoolkit | 14.8B | 28 | 3.36 GiB – 27.52 GiB | 185k |
| gemma-4-12b-heretic-abliterated | culturerevolt | 12.0B | 41 | 2.78 GiB – 11.80 GiB | 182k |
| Qwen3-235B-A22BMoE | Qwen | 235B | 35 | 79.81 GiB – 437.99 GiB | 178k |
| gpt-oss-120bMoE | openai | 120B | 15 | 58.27 GiB – 60.88 GiB | 159k |
| TinyLlama-1.1B-Chat-v1.0 | TinyLlama | 1.1B | 26 | 0.45 GiB – 2.05 GiB | 156k |
| Qwen2.5-14B-Instruct | Qwen | 14.8B | 32 | 4.99 GiB – 27.52 GiB | 148k |
| Mistral-Nemo-Instruct-2407 | mistralai | 12.2B | 35 | 4.13 GiB – 45.63 GiB | 146k |
| Phi-4-mini-instruct | microsoft | 3.8B | 34 | 1.40 GiB – 7.15 GiB | 142k |
| SmolLM2-135M-Instruct | HuggingFaceTB | 135M | 41 | 0.08 GiB – 0.25 GiB | 138k |
| Llama-3.3-70B-Instruct | meta-llama | 70.6B | 52 | 14.77 GiB – 131.43 GiB | 138k |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | nvidia | 33.0B | 17 | 17.23 GiB – 58.84 GiB | 119k |
| gemma-3-27b-it | 27.4B | 48 | 6.06 GiB – 50.32 GiB | 118k | |
| FastContext-1.0-4B-SFT | ShaunGves | 4.0B | 43 | 0.98 GiB – 7.50 GiB | 116k |
| DeepSeek-R1-Distill-Qwen-7B | deepseek-ai | 7.6B | 35 | 2.59 GiB – 28.38 GiB | 114k |
| GLM-4.6V-Flash | zai-org | 10.3B | 47 | 2.98 GiB – 17.52 GiB | 113k |
| Qwen2.5-Coder-3B-Instruct | Qwen | 3.1B | 32 | 1.06 GiB – 5.75 GiB | 110k |
| Mistral-Small-24B-Instruct-2501 | mistralai | 23.6B | 47 | 6.71 GiB – 87.82 GiB | 110k |
| DeepSeek-R1-Distill-Llama-70B | deepseek-ai | 70.6B | 48 | 14.79 GiB – 131.43 GiB | 110k |
| Mistral-7B-Instruct-v0.3 | mistralai | 7.2B | 40 | 1.50 GiB – 27.00 GiB | 110k |
| Meta-Llama-3-8B-Instruct | meta-llama | 8.0B | 34 | 1.88 GiB – 7.95 GiB | 110k |
| Ternary-Bonsai-8B-unpacked | prism-ml | 8.2B | 3 | 2.03 GiB – 15.26 GiB | 108k |
| Qwen-Image-Edit-Rapid-AIO | Phr00t | 20.4B | 72 | 4.36 GiB – 38.05 GiB | 103k |
| Qwen2.5-Coder-1.5B-Instruct | Qwen | 1.5B | 32 | 0.56 GiB – 2.88 GiB | 103k |
| DeepSeek-R1-Distill-Qwen-14B | deepseek-ai | 14.8B | 37 | 4.38 GiB – 55.03 GiB | 103k |
| Qwen2.5-72B-Instruct | Qwen | 72.7B | 29 | 22.11 GiB – 72.21 GiB | 99k |
| Llama-3.1-70B-Instruct | meta-llama | 70.6B | 46 | 14.29 GiB – 69.83 GiB | 97k |
| Ministral-3-14B-Reasoning-2512 | mistralai | 13.9B | 27 | 3.21 GiB – 25.17 GiB | 96k |
| phi-4 | microsoft | 14.7B | 37 | 4.18 GiB – 54.61 GiB | 96k |
| gemma-3-270m-it | 268M | 39 | 0.17 GiB – 0.51 GiB | 92k | |
| umt5-xxl | 5.7B | 28 | 2.36 GiB – 21.17 GiB | 92k | |
| DeepSeek-R1-Distill-Qwen-1.5B | deepseek-ai | 1.8B | 41 | 0.65 GiB – 6.63 GiB | 92k |
| LFM2.5-8B-A1BMoE | LiquidAI | 8.5B | 22 | 2.40 GiB – 15.78 GiB | 91k |
| gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking | DavidAU | 31.3B | 36 | 6.66 GiB – 30.39 GiB | 91k |
| SmolVLM-500M-Instruct | HuggingFaceTB | 507M | 2 | 0.41 GiB – 0.76 GiB | 89k |
| QwQ-32B | Qwen | 32.8B | 27 | 7.16 GiB – 122.07 GiB | 88k |
| Llama-3.1-8B | meta-llama | 8.0B | 25 | 2.96 GiB – 14.97 GiB | 88k |
| tinygemma3_cifar | ngxson | 39M | 1 | 0.04 GiB – 0.04 GiB | 87k |
| Qwen3.6-14B-A3B-FableVibesMoE | tvall43 | 13.8B | 6 | 4.96 GiB – 13.65 GiB | 84k |
| EXAONE-4.0-32B | LGAI-EXAONE | 32.0B | 31 | 8.96 GiB – 59.62 GiB | 82k |