Blog Promote Sign in Sign up

Catalogs

Models

3,545 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. MM1.5 Apple MM1.5 is Apple Research’s refinement of the MM1 multimodal recipe. It keeps the same encoder–decode… Text · Open weights Open weights
  2. Mochi 1 Genmo Mochi 1 is Genmo's open text-to-video model, a 10B asymmetric diffusion transformer released under… Video · Open weights Open weights
  3. Molmo 2 Ai2 Molmo 2 is AI2’s open 4B/7B/8B multimodal model for images and video, delivering state-of-the-art g… Text · Open weights Open weights
  4. Moondream 1 Moondream Small, efficient open-source vision-language model designed to run broadly on many devices. Multimodal · Open weights Open weights
  5. moondream 2 Moondream Moondream 2 is a small open vision-language model designed to run efficiently across many environme… Multimodal · Open weights Open weights
  6. 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
  7. Motion 1.0 Leonardo Interactive Motion 1.0 is the original short-clip image-to-video generator for quick motion studies and social… Video · Open weights Open weights
  8. Motion 2.0 Fast Leonardo Interactive Motion 2.0 Fast is a quick-render profile for Motion 2.0 that prioritizes speed and throughput. Video · Open weights Open weights
  9. MOVA OpenMOSS Open source foundation model that jointly generates video and audio in one pass, achieving tightly… Video · Open weights Open weights
  10. MultiWorld SReal AI MultiWorld is a scalable multi-agent, multi-view video world model for action-controllable simulati… Video · Open weights Open weights
  11. MuScriptor Mirelo AI An open-source multi-instrument audio-to-MIDI transcription model that converts full song mixes int… Audio · Open weights Open weights
  12. Muse Image Meta Platforms Muse Image is Meta's agentic image generation model. Rather than mapping prompts directly to pixels… Image · Open weights Open weights
  13. Muse Spark Meta Platforms Muse Spark is Meta Superintelligence Labs’ first model, built as a fast multimodal assistant for ev… Text · Open weights Open weights
  14. Muse Spark 1.1 Meta Platforms Muse Spark 1.1 is a multimodal reasoning model built for agentic tasks, with strengths in tool use,… Multimodal · Open weights Open weights
  15. Muse Video Preview Meta Platforms Muse Video is Meta's preview video generation model, built on the same pretraining base as Muse Ima… Video · Open weights Open weights
  16. Namazu Sakana AI Namazu is a Japanese specialized large language model from Sakana AI, built through post training o… Multimodal · Open weights Open weights
  17. Nanobanana 2 Google DeepMind Nanobanana 2 is Gemini 3.1 Flash Image, Google’s faster upgraded image-generation and editing model… Multimodal · Open weights Open weights
  18. Nemotron Nano 2 NVIDIA Nemotron-Nano 2 is NVIDIA’s ultra-compact LLM tuned for on-device and edge deployment. It delivers… Text · Open weights Open weights
  19. Nemotron-4 NVIDIA Nemotron-4 is NVIDIA’s open-weight LLM family (from compact to 340B) built for high-quality reasoni… Text · Open weights Open weights
  20. Nova 3 Deepgram Nova 3 is Deepgram's flagship speech to text API built for enterprise voice AI. It delivers real ti… Audio · Open weights Open weights
  21. NVIDIA Alpamayo 2 Super NVIDIA A 32-billion-parameter open reasoning-based vision language action (VLA) model for level 4 autonomo… Multimodal · Open weights Open weights
  22. NVIDIA Cosmos 3 NVIDIA Cosmos 3 is NVIDIA’s open physical-AI foundation model for vision reasoning, world simulation, mult… Multimodal · Open weights Open weights
  23. Odyssey 3 Odyssey A foundation world model trained on visual observations of the world. It learns physics, dynamics,… Multimodal · Open weights Open weights
  24. Odyssey-2 Odyssey Odyssey-2 is a general purpose world model that generates real time interactive video simulations f… Video · Open weights Open weights
  25. OLMo Ai2 OLMo is Ai2's fully open language model, released in February 2024 in 1B and 7B sizes. Unlike most… Text · Open weights Open weights
  26. Olmo 3 Ai2 Olmo 3 is Ai2's fully open model family in 7B and 32B sizes, shipped as Base, Instruct, Think and R… Text · Open weights Open weights
  27. OmniScient Model ByteDance OmniScient Model (OSM) is an open-ended visual recognition approach that predicts free-form class l… Text · 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. OpenRouter Text to Speech OpenRouter OpenRouter TTS is OpenRouter’s unified text-to-speech interface for accessing multiple speech-gener… Multimodal · Open weights Open weights
  30. Orca Microsoft AI model by Microsoft Text · Open weights Open weights
  31. Orca (BAAI) Beijing Academy of Artificial Intelligence (BAAI) Orca is a world foundation model that learns a unified latent world state from multimodal signals t… Multimodal · Open weights Open weights
  32. P Image Ideogram Ideogram AI P-Image-Ideogram is a fast text-to-image model built with Pruna AI, offering four quality tiers (Ve… Image · Open weights Open weights
  33. P Video Pruna AI P-Video is an image-to-video model that supports text, image, and audio inputs and can generate vid… Video · Open weights Open weights
  34. p video avatar Pruna AI p-video-avatar is Pruna’s talking-head video generation model for creating speaking avatar videos f… Multimodal · Open weights Open weights
  35. P-1 Respan P-1 is Respan's privacy model built for detecting and redacting sensitive information in text. Resp… Text · Open weights Open weights
  36. PAI Utopai Studios PAI is Utopai Studios’ cinematic long-form AI video model for scene-based storytelling. It is built… Video · Open weights Open weights