Blog Promote Sign in Sign up

Catalogs

Models

4,400 in the directory.

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source
Open weights Closed On Hugging Face
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. Nemotron Labs Audex 30B A3B NVIDIA Nemotron-Labs-Audex-30B-A3B is a unified audio-text large language model from NVIDIA built on a 30B… Multimodal · Open weights 512 HF downloads
  2. Bonsai 27B AWQ 4bit PrismML Bonsai 27B AWQ 4bit is a 4-bit AWQ quantized release of Prism ML's Bonsai 27B, a 27 billion paramet… Multimodal · Open weights 504 HF downloads
  3. Macaron V1 Venti Macaron Macaron-V1-Venti is a 748 billion parameter agent model post-trained on GLM-5.2, combining a frozen… Text · Open weights 504 HF downloads
  4. Macaron V1 Coding Venti Macaron Macaron-V1-Coding-Venti is a coding-specialized build of Macaron-V1-Venti with the coding LoRA spec… Coding · Open weights 501 HF downloads
  5. Baichuan M3 235B Baichuan Intelligent Technology Baichuan-M3-235B is a medical-enhanced large language model trained to model clinical inquiry and d… Text · Open weights 499 HF downloads
  6. Claude Sonnet 5 Anthropic Claude Sonnet 5 is Anthropic's large language model, the most agentic Sonnet released so far. It pl… Multimodal · Closed 481 HF downloads
  7. Macaron V1 Tall Macaron Macaron-V1-Tall is a 50 billion parameter agent model post-trained from Qwen 3.6, using the same Mi… Text · Open weights 473 HF downloads
  8. Hunyuan-Large Tencent Hunyuan-Large is Tencent’s flagship large language model in the Hunyuan family. It’s built for adva… Text · Open weights 468 HF downloads
  9. sarashina 2.2 tts SB Intuitions sarashina2.2-tts is SB Intuitions’ Japanese-centric large-language-model-based text-to-speech syste… Multimodal · Open weights 466 HF downloads
  10. Ulam-1-Small Ulam.ai Ulam-1-Small is a 3.086B-parameter open-weight language model from Ulam AI, released under the MIT… Text · Open weights 417 HF downloads
  11. AquilaChat Beijing Academy of Artificial Intelligence (BAAI) AI model by Beijing Academy of Artificial Intelligence (BAAI) Text · Open weights 412 HF downloads
  12. Lucy Edit Decart AI Lucy Edit by Decart AI is a text-guided video editor. You upload a clip, describe the change in nat… Video · Closed 408 HF downloads
  13. SkyReels V3 Skywork AI Long-form video extension engine that analyzes scene semantics and motion to extend clips with cohe… Multimodal · Open weights 406 HF downloads
  14. Hunyuan MT Chimera 7B Tencent Hunyuan-MT-Chimera-7B is Tencent’s open-source translation ensemble model that combines multiple tr… Text · Open weights 404 HF downloads
  15. Kanana 1.5 Naver Kanana-1.5-v-3B is a 3B-parameter vision–language model in Kakao’s Kanana line. It can process both… Text · Closed 399 HF downloads
  16. ERNIE 4.5-300B-A47B Baidu ERNIE 4.5-300B-A47B is Baidu’s frontier Mixture-of-Experts ERNIE 4.5 variant—~300B total parameters… Text · Closed 369 HF downloads
  17. Lizzy 7B Flower Labs Lizzy 7B is an open-weight 7 billion parameter language model from Flower Labs, built in the UK and… Text · Open weights 368 HF downloads
  18. Bielik 11B v2.6 Instruct SpeakLeash Bielik-11B-v2.6-Instruct is a Polish-focused 11B instruction model from SpeakLeash, aimed at strong… Text · Open weights 366 HF downloads
  19. Penguin VL 2B Tencent Penguin-VL-2B is a compact vision-language model that uses an LLM-based vision encoder to push effi… Multimodal · Open weights 366 HF downloads
  20. LFM2-Audio-1.5 Liquid AI LFM2-Audio-1.5 is a unified audio foundation model for real-time speech, music, and sound effects.… Multimodal · Open weights 328 HF downloads
  21. SenseNova Vision 7B MoT SenseTime SenseNova-Vision-7B-MoT is a unified multimodal model for computer vision. It reformulates object d… Multimodal · Open weights 320 HF downloads
  22. Penguin VL 8B Tencent Penguin-VL-2B is a compact vision-language model that uses an LLM-based vision encoder to push effi… Multimodal · Open weights 319 HF downloads
  23. MolmoMotion 4B H1 F32 Ai2 4B vision-language model that forecasts 3D point trajectories from a single RGB observation frame,… Multimodal · Open weights 313 HF downloads
  24. MiroThinker v1.5 MiroMindAI MiroThinker v1.5 is an open-source deep research agent that orchestrates tools and web search to pl… Text · Closed 272 HF downloads
  25. Maincoder-1B Maincode Maincoder-1B is Maincode’s 1B-parameter transformer coding model, optimized for Python code generat… Text · Closed 267 HF downloads
  26. LongCat Next Meituan LongCat Next is a multimodal LongCat model focused on compact yet capable visual and speech underst… Multimodal · Open weights 265 HF downloads
  27. Phonon 1 Fermion Research Phonon 1 is an open speech recognition model for English. It downloads in 415 MB and runs on a lapt… Audio · Closed 262 HF downloads
  28. Qianfan-VL-3B Baidu Qianfan-VL-3B is Baidu’s lightweight VLM for cost-sensitive, real-time multimodal apps. It processe… Text · Closed 252 HF downloads
  29. OmniVinci NVIDIA OmniVinci is NVIDIA’s 9B omni-modal LLM that jointly understands images, video, audio, and text, ac… Image · Open weights 241 HF downloads
  30. LingBot Video Dense 1.3B Robbyant LingBot-Video-Dense is a 1.3 billion parameter dense video generation model from the open source Li… Video · Open weights 237 HF downloads
  31. Smaug Flash Abacus.AI Smaug Flash is a fine tune of DeepSeek V4 Flash 0731 optimized for enterprise self improving agents… Coding · Open weights 236 HF downloads
  32. Mixtral 8x22B Mistral AI Mixtral 8x22B is a sparse mixture-of-experts language model that routes tokens to a subset of exper… Text · Open weights 223 HF downloads
  33. Stockmark 2 100b instruct Stockmark Stockmark-2-100B-Instruct is a 100B Japanese-focused instruction model built from scratch, trained… Text · Open weights 223 HF downloads
  34. LongCat Flash Thinking Meituan Large reasoning model built on a 560B MoE backbone, activating about 18.6 to 31.3B parameters for a… Text · Open weights 216 HF downloads
  35. Dramabox Resemble AI DramaBox is Resemble AI’s expressive text-to-speech and voice-cloning model for turning screenplay-… Multimodal · Closed 211 HF downloads
  36. Motif 2 12.7B Reasoning Motif Technologies Motif 2 12.7B Reasoning is a 12.7 billion parameter reasoning focused language model from Motif Tec… Text · Open weights 208 HF downloads