Blog Promote Sign in Sign up

Catalogs

Models

3,241 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. 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
  2. Chinchilla Google DeepMind Chinchilla is DeepMind’s 70B language model used to demonstrate compute-optimal scaling with more t… Text · Open weights 2 HF downloads
  3. SkyReels V1 Skywork AI SkyReels V1 is a human-centric video foundation model tuned for cinematic, character-focused genera… Video · Open weights 2 HF downloads
  4. Vchitect 2.0 Shanghai AI Laboratory Vchitect-2.0 is a parallel-transformer text-to-video diffusion model that scales to large video dat… Video · Open weights 2 HF downloads
  5. 7 DreamShaper Stability AI DreamShaper 7 is a versatile SD checkpoint that balances realism and illustration for all purpose c… Image · Open weights Open weights
  6. ACE Step v1.5 StepFun ACE-STEP v1.5 is an open source, super fast music foundation model that uses a hybrid language mode… Audio · Open weights Open weights
  7. Apertus 8B Instruct 2509 Swiss AI Initiative Apertus 8B Instruct 2509 is an 8B parameter open-source instruction-tuned language model pretrained… Text · Open weights Open weights
  8. AURA Huawei AURA is a real-time multimodal streaming system for continuous video understanding with speech inte… Multimodal · Open weights Open weights
  9. Baichuan 13B Baichuan Intelligent Technology Baichuan-13B is a bilingual Chinese-English 13B-parameter model released in Base (pretrained) and C… Text · Open weights Open weights
  10. 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
  11. Brainiac Nate Lorenzen Brainiac is an open-source neuroscience-based visual-content analysis tool for thumbnails, landing… Multimodal · Open weights Open weights
  12. DreamID-Omni Guoxu1233 DreamID-Omni is a human-centric audio-video generation framework that supports reference-conditione… Multimodal · Open weights Open weights
  13. FastVLM Apple FastVLM is Apple’s lightweight vision-language model built for real-time multimodal apps. It ingest… Text · Open weights Open weights
  14. FlowRVS xmz111 FlowRVS is a referring video object segmentation method that learns a text-conditioned continuous f… Multimodal · Open weights Open weights
  15. GLM-130B Z.ai AI model by Z.ai Text · Open weights Open weights
  16. Glyph Tsinghua University Glyph is a symbol-aware language model for code and math. It emphasizes structured reasoning, tool… Text · Open weights text to image pipeline
  17. Harrier OSS v1 Microsoft Harrier is Microsoft’s new open-source text embedding model series for retrieval, grounding, and ag… Text · Open weights Open weights
  18. HunyuanCustom Tencent HunyuanCustom is Tencent’s customization framework for the Hunyuan model family. It lets enterprise… Video · Open weights image to video pipeline
  19. HunyuanVideo Avatar Tencent HunyuanVideo-Avatar is Tencent’s talking-avatar video generator. It turns text or audio into lifeli… Video · Open weights image to video pipeline
  20. LingBot Depth Robbyant LingBot-Depth is a depth completion model that refines noisy or incomplete depth sensor data into h… 3D · Open weights depth estimation pipeline
  21. LingBot World Base Cam Robbyant LingBot World Base Cam is an open source image to video world model that generates long, real time… Video · Open weights image to video pipeline
  22. LingBot-World-Base (Act) Preview Robbyant LingBot-World-Base (Act) is an open source world model that generates interactive videos from an im… Video · Open weights image to video pipeline
  23. Llama 3 Motif 102B Instruct Motif Technologies Llama 3 Motif 102B Instruct is a 102-billion-parameter bilingual (Korean/English) large language mo… Text · Open weights text generation pipeline
  24. Meridian Viggle AI Meridian is a video to video model that regenerates existing footage from a new camera viewpoint an… Video · Open weights video to video pipeline
  25. MM1 Apple MM1 is Apple Research’s multimodal LLM blueprint: a vision encoder feeding a text decoder via cross… Text · Open weights Open weights
  26. Moonshine Moonshine AI Moonshine's AI offers a voice interface that runs locally, so all your data remains 100% under your… Audio · Open weights automatic speech recognition pipeline
  27. MuScriptor Mirelo AI An open-source multi-instrument audio-to-MIDI transcription model that converts full song mixes int… Audio · Open weights Open weights
  28. OpenHelix OpenHelix OpenHelix is an open dual-system vision-language-action (VLA) approach for robotic manipulation tha… Text · Open weights Open weights
  29. PaperBanana dwzhu-pku PaperBanana is an agentic framework that turns raw scientific content into publication-ready method… Multimodal · Open weights Open weights
  30. Persimmon Humans& Persimmon is a research-preview user model from humans& that simulates realistic human behavior in… Text · Open weights Open weights
  31. 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
  32. Phi 3.5 MoE Gentext Group Phi-3.5-MoE is Microsoft’s open-weight Mixture-of-Experts model (16×3.8B, ~6.6B active) built for s… Text · Open weights Open weights
  33. R1 1776 Perplexity R1 1776 is Perplexity’s open-source, post-trained variant of DeepSeek-R1 that removes CCP-aligned c… Text · Open weights Open weights
  34. SOMA-X NVIDIA SOMA-X is NVIDIA’s Apache 2.0 human-body-model unification framework for mapping multiple parametri… 3D · Open weights robotics pipeline
  35. talkie 1930 13b base talkie talkie is a 13B vintage language model trained only on pre-1931 English text. It is built to act as… Text · Open weights Open weights
  36. Ternary Bonsai 27B Unpacked PrismML Ternary Bonsai 27B is a 27B parameter multimodal language model from PrismML, built on a hybrid lin… Multimodal · Open weights Open weights