Loading models…
1,163,950 models indexed
| # | Model | Task | Library | Params | ↓ 30d | ❤ | Updated |
|---|---|---|---|---|---|---|---|
| 1 | google/gemma-4-12B-it google· apache-2.0 | any-to-any | transformers | 12.0B | 581.4k | 849 | 6d |
| 2 | nvidia/LocateAnything-3B nvidia· other· arXiv ×8 | image-text-to-text | transformers | 3.8B | 123.9k | 1.8k | 1d |
| 3 | unsloth/gemma-4-12b-it-GGUF unsloth· apache-2.0 | image-text-to-text | — | 11.9B | 660.1k | 540 | 23h |
| 4 | google/gemma-4-12B google· apache-2.0 | any-to-any | transformers | 12.0B | 122.5k | 494 | 6d |
| 5 | ideogram-ai/ideogram-4-fp8 ideogram-ai· other | text-to-image | diffusers | — | 5.9k | 456 | 6d |
| 6 | bosonai/higgs-audio-v3-tts-4b bosonai· other | text-to-speech | transformers | 4.7B | 16.2k | 302 | 5d |
| 7 | ideogram-ai/ideogram-4-nf4 ideogram-ai· other | text-to-image | diffusers | — | 5.3k | 297 | 5d |
| 8 | nvidia/nemotron-3.5-asr-streaming-0.6b nvidia· other· arXiv ×2 | automatic-speech-recognition | nemo | — | 4.2k | 331 | 4d |
| 9 | HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS· apache-2.0 | image-text-to-text | — | 34.7B | 3.0M | 1.6k | 1mo |
| 10 | sapientinc/HRM-Text-1B sapientinc· apache-2.0· arXiv ×1 | text-generation | transformers | 1.2B | 133.4k | 739 | 20d |
| 11 | CohereLabs/North-Mini-Code-1.0 CohereLabs· apache-2.0 | text-generation | transformers | 30.5B | 1.8k | 207 | 21h |
| 12 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 nvidia· other | text-generation | transformers | 560.5B | 56.9k | 182 | 9h |
| 13 | MisoLabs/MisoTTS MisoLabs | text-to-speech | pytorch | — | — | 179 | 8d |
| 14 | OBLITERATUS/Gemma-4-12B-OBLITERATED OBLITERATUS· gemma | text-generation | transformers | 12.0B | 8.1k | 187 | 1d |
| 15 | unsloth/gemma-4-12B-it-qat-GGUF unsloth· apache-2.0 | any-to-any | transformers | 11.9B | 127.3k | 177 | 2h |
| 16 | nex-agi/Nex-N2-Pro nex-agi· apache-2.0 | text-generation | transformers | 396.8B | 783 | 170 | 1d |
| 17 | google/magenta-realtime-2 google· cc-by-4.0· arXiv ×4 | text-to-audio | magenta-realtime-2 | — | 18.2k | 166 | 5d |
| 18 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 nvidia· other | text-generation | transformers | 335.0B | 71.8k | 156 | 8h |
| 19 | stepfun-ai/Step-3.7-Flash stepfun-ai· apache-2.0 | image-text-to-text | transformers | 201.4B | 46.7k | 362 | 7d |
| 20 | nex-agi/Nex-N2-mini nex-agi· apache-2.0 | text-generation | transformers | 35.1B | 748 | 126 | 1d |
| 21 | ByteDance/Bernini-R ByteDance· arXiv ×1 | image-text-to-video | — | — | 281 | 203 | 8d |
| 22 | unsloth/gemma-4-26B-A4B-it-qat-GGUF unsloth· apache-2.0 | image-text-to-text | transformers | 25.2B | 96.1k | 123 | 2h |
| 23 | LiquidAI/LFM2.5-8B-A1B LiquidAI· other· arXiv ×1 | text-generation | transformers | 8.5B | 137.1k | 577 | 4d |
| 24 | Comfy-Org/Ideogram-4 Comfy-Org | — | — | — | — | 120 | 5d |
| 25 | deepseek-ai/DeepSeek-V4-Pro deepseek-ai· mit | text-generation | transformers | 861.6B | 4.3M | 4.8k | 2d |
| 26 | JetBrains/Mellum2-12B-A2.5B-Thinking JetBrains· apache-2.0· arXiv ×1 | text-generation | transformers | 12.1B | 17.6k | 277 | 8d |
| 27 | google/gemma-4-12B-it-qat-q4_0-gguf google· apache-2.0 | any-to-any | transformers | 11.9B | 63.0k | 119 | 4d |
| 28 | jdopensource/JoyAI-Echo jdopensource· other | text-to-video | ltx-video | — | 4.5k | 120 | 2d |
| 29 | nvidia/Cosmos3-Nano nvidia· other | — | cosmos | 15.8B | 36.7k | 218 | 9d |
| 30 | huihui-ai/Huihui-gemma-4-12B-it-abliterated huihui-ai· apache-2.0 | any-to-any | transformers | 12.0B | 5.7k | 129 | 2d |
| 31 | unsloth/Qwen3.6-27B-MTP-GGUF unsloth· apache-2.0 | image-text-to-text | transformers | 27.3B | 1.1M | 704 | 15d |
| 32 | google/gemma-4-31B-it google· apache-2.0 | image-text-to-text | transformers | 32.7B | 10.1M | 3.0k | 7d |
| 33 | PaddlePaddle/PaddleOCR-VL-1.6 PaddlePaddle· apache-2.0· arXiv ×1 | image-text-to-text | PaddleOCR | 959M | 10.1k | 285 | 5d |
| 34 | SulphurAI/Sulphur-2-base SulphurAI | text-to-video | diffusers | 9.0B | 1.6M | 1.6k | 5d |
| 35 | Jiunsong/supergemma4-26b-uncensored-gguf-v2 Jiunsong· gemma | text-generation | — | 25.2B | 141.2k | 795 | 1mo |
| 36 | google/gemma-4-12B-it-assistant google· apache-2.0 | any-to-any | transformers | 423M | 19.6k | 77 | 6d |
| 37 | XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash XiaomiMiMo | text-generation | transformers | — | 48 | 70 | 2d |
| 38 | deepseek-ai/DeepSeek-V4-Flash deepseek-ai· mit | text-generation | transformers | 158.1B | 2.8M | 1.5k | 2d |
| 39 | zai-org/SCAIL-2 zai-org· arXiv ×1 | image-to-video | diffusers | — | — | 68 | 1d |
| 40 | Qwen/Qwen3.6-27B Qwen· apache-2.0 | image-text-to-text | transformers | 27.8B | 5.3M | 1.7k | 1mo |
| 41 | black-forest-labs/FLUX.1-dev black-forest-labs· other | text-to-image | diffusers | — | 984.0k | 13.1k | 11mo |
| 42 | LiconStudio/LTX-2.3-Multiple-Subject-Reference LiconStudio· apache-2.0 | — | diffusers | — | 4.2k | 96 | 3d |
| 43 | Qwen/Qwen3.6-35B-A3B Qwen· apache-2.0 | image-text-to-text | transformers | 36.0B | 5.3M | 2.1k | 1mo |
| 44 | unsloth/gemma-4-31B-it-qat-GGUF unsloth· apache-2.0 | image-text-to-text | transformers | 30.7B | 51.0k | 59 | 2h |
| 45 | pyannote/speaker-diarization-3.1 pyannote· mit· arXiv ×2 | automatic-speech-recognition | pyannote-audio | — | 8.1M | 2.2k | 2y |
| 46 | circlestone-labs/Anima circlestone-labs· other | — | diffusion-single-file | — | 763.8k | 1.7k | 11d |
| 47 | pat-jj/harness-1 pat-jj· arXiv ×1 | text-generation | transformers | 20.9B | 781 | 68 | 2d |
| 48 | nvidia/Qwen3.6-35B-A3B-NVFP4 nvidia· apache-2.0 | text-generation | Model Optimizer | 18.7B | 1.4M | 208 | 11d |
| 49 | nvidia/Cosmos3-Super nvidia· other | — | cosmos | 64.6B | 30.0k | 164 | 4d |
| 50 | CohereLabs/BLS-Mini-Code-1.0 CohereLabs | — | — | 30.5B | 1.8k | 57 | 1d |