Promote Sign in Sign up

Catalogs

Models

652 matched .

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

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source · filters active
Open weights Closed On Hugging Face Clear filters
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. 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
  2. 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
  3. 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
  4. Dramabox Resemble AI DramaBox is Resemble AI’s expressive text-to-speech and voice-cloning model for turning screenplay-… Multimodal · Closed 211 HF downloads
  5. Zamba2 VL 7B Zyphra AI Zamba2-VL-7B is Zyphra’s open 7B-class vision-language model for single-image and multi-image under… Multimodal · Open weights 202 HF downloads
  6. Matrix Game 3.0 Skywork AI Matrix-Game 3.0 is Skywork’s open-source interactive world model for real-time long-form video gene… Multimodal · Open weights 188 HF downloads
  7. LongCat Flash Omni Meituan 560B parameter omni-modal MoE model (about 27B active) for real time audio-visual interaction, buil… Multimodal · Open weights 186 HF downloads
  8. HunyuanVideo I2V Tencent HunyuanVideo I2V is an image-to-video generation model based on the HunyuanVideo framework, built t… Multimodal · Open weights 145 HF downloads
  9. BioReason Pro bowang-lab BioReason-Pro SFT is a supervised fine-tuned checkpoint of BioReason-Pro, a multimodal reasoning LL… Multimodal · Open weights 134 HF downloads
  10. LingBot VLA 2.0 Robbyant LingBot VLA 2.0 is a 6B parameter Vision Language Action foundation model that converts camera imag… Multimodal · Open weights 133 HF downloads
  11. Ornstein Hermes 3.6 27b MLX 8bit GestaltLabs Ornstein-Hermes-3.6-27b-MLX-8bit is Gestalt Labs’ 8-bit MLX quantization of Ornstein-Hermes-3.6-27b… Multimodal · Open weights 131 HF downloads
  12. LingBot VLA 4B Depth Robbyant LingBot VLA 4B Depth is a vision language action foundation model for robot manipulation. Pretraine… Multimodal · Open weights 111 HF downloads
  13. Proxy Lite 3B Convergence AI A 3B vision-language, web-browsing agent model fine-tuned from Qwen2.5-VL-3B-Instruct for automated… Multimodal · Open weights 104 HF downloads
  14. Huihui 4 8B A4B HuiHui ai Huihui4-8B-A4B is a lightweight pruned MoE conversational model based on Gemma-4-26B-A4B-it. It is… Multimodal · Open weights 82 HF downloads
  15. Huihui 4 8B A4B v2 HuiHui ai Huihui4-8B-A4B-v2 is a lightweight pruned MoE conversational model derived from Gemma-4-26B-A4B-it.… Multimodal · Open weights 82 HF downloads
  16. OpenAudio S1 Fish Audio OpenAudio S1 is a text to speech model that generates natural human speech from text, with native s… Multimodal · Closed 65 HF downloads
  17. RynnBrain Alibaba AI model by Alibaba Multimodal · Closed 63 HF downloads
  18. Xiaomi Robotics U0 Xiaomi A 38 billion parameter multimodal autoregressive model for unified embodied synthesis. It performs… Multimodal · Open weights 63 HF downloads
  19. TinyMU Xiquan Li TinyMU is a compact 229M audio-language model for music understanding and reasoning. It is designed… Multimodal · Open weights 51 HF downloads
  20. Distil Whisper Hugging Face Distil Whisper is a distilled version of OpenAI's Whisper speech recognition model, roughly six tim… Multimodal · Closed 37 HF downloads
  21. UGC VideoCaptioner Memories.ai UGC VideoCaptioner is a 3B parameter omni model that writes detailed, paragraph style captions for… Multimodal · Open weights 13 HF downloads
  22. Reka Edge Reka AI Reka Edge is Reka’s 7B vision-language model engineered for edge and physical-AI deployment, with s… Multimodal · Open weights 9 HF downloads
  23. Protenix ByteDance Protenix is ByteDance’s open-source biomolecular structure prediction model family for high-accurac… Multimodal · Open weights 7 HF downloads
  24. Baichuan Audio Baichuan Intelligent Technology Baichuan-Audio is an end-to-end speech interaction model that unifies audio understanding and audio… Multimodal · Open weights 6 HF downloads
  25. Xiaomi-Robotics-1 Xiaomi Xiaomi-Robotics-1 is a vision-language-action robot foundation model pre-trained on over 100,000 ho… Multimodal · Open weights 3 HF downloads
  26. AURA Huawei AURA is a real-time multimodal streaming system for continuous video understanding with speech inte… Multimodal · Open weights Open weights
  27. BGE VL Beijing Academy of Artificial Intelligence (BAAI) BGE VL is BAAI’s multimodal retrieval family for image-text search. It includes lightweight CLIP-ba… Multimodal · Open weights Open weights
  28. Brainiac Nate Lorenzen Brainiac is an open-source neuroscience-based visual-content analysis tool for thumbnails, landing… Multimodal · Open weights Open weights
  29. DreamID-Omni Guoxu1233 DreamID-Omni is a human-centric audio-video generation framework that supports reference-conditione… Multimodal · Open weights Open weights
  30. FlowRVS xmz111 FlowRVS is a referring video object segmentation method that learns a text-conditioned continuous f… Multimodal · Open weights Open weights
  31. Gemini 3.6 Flash Google Gemini 3.6 Flash is Google's workhorse model in the Gemini 3 series, a natively multimodal reasonin… Multimodal · Closed Closed weights
  32. Mega ASR Shanghai AI Laboratory Mega-ASR is an open-source robust automatic speech recognition model built for difficult real-world… Multimodal · Closed automatic speech recognition pipeline
  33. PaperBanana dwzhu-pku PaperBanana is an agentic framework that turns raw scientific content into publication-ready method… Multimodal · Open weights Open weights
  34. PersonaLive GVC Lab PersonaLive is a real-time diffusion model for expressive portrait image animation in live streamin… Multimodal · Open weights image to video pipeline
  35. Qwen 3.7 Plus Alibaba Qwen3.7-Plus is Alibaba Qwen’s multimodal agent model that unifies vision and language for agentic… Multimodal · Closed Closed weights
  36. SANA WM (Bidirectional) NVIDIA SANA-WM Bidirectional is Efficient-Large-Model’s open-source 2.6B image-to-video world model for 72… Multimodal · Closed image to video pipeline