Loading models…
1,262,672 models indexed
| # | Model | Task | Library | Params | ↓ 30d | ❤ | Updated |
|---|---|---|---|---|---|---|---|
| 2001 | openbmb/MiniCPM-V-4.6-gguf openbmb· apache-2.0· arXiv ×4 | image-text-to-text | transformers | 752M | 38.2k | 47 | 3mo |
| 2002 | openbmb/MiniCPM-RobotTrack openbmb· apache-2.0 | robotics | transformers | 450M | 536 | 132 | 1mo |
| 2003 | openbmb/MiniCPM-RobotManip openbmb· apache-2.0 | robotics | transformers | 1.5B | 1.0k | 180 | 1mo |
| 2004 | openbmb/BitCPM4-CANN-8B-gguf openbmb | text-generation | transformers | — | 256 | 7 | 3mo |
| 2005 | openai/clip-vit-large-patch14 openai· arXiv ×2 | zero-shot-image-classification | transformers | 428M | 24.9M | 2.0k | 3y |
| 2006 | nyralabs/CrisperWhisper2.0_large_pro nyralabs | — | — | — | 43 | 15 | 1mo |
| 2007 | nyralabs/CrisperWhisper2.0_large nyralabs· other· arXiv ×1 | automatic-speech-recognition | crisperwhisper | 1.5B | 22.7k | 101 | 1mo |
| 2008 | nvidia/nemotron-ocr-v2 nvidia· other | image-to-text | — | — | 6.9k | 238 | 3mo |
| 2009 | nvidia/magpie_tts_multilingual_357m nvidia· other· arXiv ×7 | text-to-speech | nemo | 284M | 7.4k | 214 | 5d |
| 2010 | nvidia/kokoro-82M-onnx-opt nvidia· arXiv ×2 | — | — | — | — | 34 | 3mo |
| 2011 | nvidia/instant-nurec nvidia· other· arXiv ×3 | image-to-3d | — | — | 321 | 24 | 1mo |
| 2012 | nvidia/Riva-Translate-4B-Instruct-v2 nvidia | text-generation | transformers | 4.2B | 1.2k | 15 | 1mo |
| 2013 | nvidia/Qwen3.8-2.4T-A95B-NVFP4 nvidia· other | text-generation | Model Optimizer | 1260.8B | 903 | 12 | 10d |
| 2014 | nvidia/Qwen3.6-27B-NVFP4 nvidia· apache-2.0 | text-generation | Model Optimizer | 18.2B | 1.6M | 424 | 2mo |
| 2015 | nvidia/Qwen-Image-Flash nvidia· other· arXiv ×3 | text-to-image | diffusers | 20.4B | 1.0k | 85 | 1mo |
| 2016 | nvidia/PiD nvidia· arXiv ×1 | image-to-image | pytorch | — | 355 | 399 | 2mo |
| 2017 | nvidia/Nemotron-Labs-Diffusion-VLM-8B nvidia· other | image-text-to-text | transformers | 8.9B | 6.0k | 25 | 3mo |
| 2018 | nvidia/Nemotron-Labs-Diffusion-14B nvidia· other | text-generation | transformers | 13.5B | 12.6k | 139 | 3mo |
| 2019 | nvidia/Nemotron-Labs-Audex-30B-A3B nvidia· other· arXiv ×1 | text-generation | transformers | — | 2.6k | 172 | 2mo |
| 2020 | nvidia/Nemotron-Labs-Audex-2B nvidia· other· arXiv ×1 | text-generation | transformers | — | 2.7k | 86 | 2mo |
| 2021 | nvidia/Nemotron-3-Embed-8B-BF16 nvidia· other· arXiv ×1 | sentence-similarity | sentence-transformers | 8.0B | 108.0k | 80 | 1mo |
| 2022 | nvidia/NVIDIA-Nemotron-Parse-v1.2 nvidia· other | image-text-to-text | transformers | 936M | 241.3k | 65 | 4mo |
| 2023 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 nvidia· other | text-generation | transformers | 560.5B | 1.6k | 25 | 3mo |
| 2024 | nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF nvidia· other· arXiv ×5 | text-generation | transformers | 4.0B | 11.0k | 203 | 6mo |
| 2025 | nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 nvidia· other· arXiv ×5 | text-generation | transformers | 4.0B | 528.4k | 114 | 5mo |
| 2026 | nvidia/NV-OneFormer nvidia· arXiv ×2 | — | — | — | — | 7 | 3mo |
| 2027 | nvidia/Gemma-4-26B-A4B-NVFP4 nvidia· apache-2.0 | text-generation | Model Optimizer | 14.4B | 1.2M | 73 | 4mo |
| 2028 | nvidia/GLM-5.1-NVFP4 nvidia· mit | text-generation | Model Optimizer | 381.5B | 58.9k | 33 | 3mo |
| 2029 | nvidia/DeepSeek-V4-Pro-NVFP4 nvidia· mit | text-generation | Model Optimizer | 910.0B | 41.9k | 59 | 3mo |
| 2030 | nvidia/Cosmos3-Super-Text2Image-4Step nvidia· other· arXiv ×1 | text-to-image | cosmos | 64.0B | 364 | 7 | 1mo |
| 2031 | nvidia/Cosmos3-Super-Text2Image nvidia· other | text-to-image | cosmos | 64.6B | 2.9k | 173 | 2mo |
| 2032 | nvidia/Cosmos3-Super-Image2Video-4Step nvidia· other· arXiv ×1 | image-to-video | cosmos | 64.0B | 2.1k | 29 | 1mo |
| 2033 | nvidia/Cosmos3-Super-Image2Video nvidia· other | image-to-video | cosmos | 64.6B | 6.5k | 148 | 2mo |
| 2034 | nvidia/Cosmos3-Super nvidia· other | — | cosmos | 64.6B | 117.7k | 233 | 2mo |
| 2035 | nvidia/Cosmos3-Nano-Policy-DROID nvidia· other | — | cosmos | 15.7B | 15.9k | 23 | 3mo |
| 2036 | nvidia/Cosmos3-Nano nvidia· other | — | cosmos | 15.8B | 342.9k | 326 | 2mo |
| 2037 | nvidia/Cosmos-H-Dreams nvidia· other· arXiv ×2 | image-to-video | nv-medtech | — | 319 | 12 | 1mo |
| 2038 | nvidia/ARDY-Core-RP-20FPS-Horizon40 nvidia· other | — | ardy | — | 1.9k | 30 | 2mo |
| 2039 | numind/NuExtract3-GGUF numind· apache-2.0 | image-text-to-text | transformers | 4.2B | 9.2k | 25 | 3mo |
| 2040 | notSnix/Step-3.7-Flash-Q4_K_M-MTP-GGUF notSnix· apache-2.0 | text-generation | gguf | 197.0B | 2.7k | 7 | 3mo |
| 2041 | nightmedia/Qwen3.6-27B-GrandWichtel-mxfp8-mlx nightmedia· apache-2.0 | image-text-to-text | transformers | 8.0B | 455 | 7 | 1mo |
| 2042 | nightmedia/Qwen3.5-9B-Holodeck-Lounge-GGUF nightmedia· apache-2.0 | image-text-to-text | transformers | 9.0B | 4.2k | 8 | 1mo |
| 2043 | nif0/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-H3-GGUF nif0· apache-2.0 | — | — | 25.2B | 40.5k | 26 | 1mo |
| 2044 | nhathoangfoto/Flux.2-Klein-9B-MatchingPose nhathoangfoto· apache-2.0 | image-text-to-image | diffusers | — | 5.4k | 25 | 3mo |
| 2045 | nex-agi/Nex-N2-Pro-fp8 nex-agi | text-generation | transformers | — | 20 | 7 | 3mo |
| 2046 | neuphonic/neutts-2e neuphonic· other | text-to-speech | — | 236M | 8.2k | 36 | 1mo |
| 2047 | nerkyor/Qwen3.6-35B-A3B-DSV4Pro-SFT-GPT56Sol-RL-Agent-GGUF nerkyor· apache-2.0 | — | — | 34.7B | 32.8k | 13 | 1mo |
| 2048 | nari-labs/Dia-1.6B nari-labs· apache-2.0· arXiv ×1 | text-to-speech | — | — | 8.7k | 2.9k | 1y |
| 2049 | mudler/rfdetr-cpp-nano mudler· apache-2.0 | object-detection | rfdetr.cpp | 30M | 674 | 9 | 3mo |
| 2050 | mudler/Qwopus3.6-35B-A3B-v1-APEX-MTP-GGUF mudler· apache-2.0 | — | — | 35.5B | 17.7k | 14 | 3mo |