Blog Promote Sign in Sign up

Catalogs

Models

1,828 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. AlphaFold 3 Google DeepMind AlphaFold 3 is Google DeepMind and Isomorphic Labs’ biomolecular structure model for predicting pro… Text · Open weights 21 HF downloads
  2. XBai o4 MetaStone AI XBai-o4 is an open large language model focused on test-time scaling and reflective reasoning impro… Text · Open weights 21 HF downloads
  3. 1 Bit Bonsai 1.7B PrismML 1-bit Bonsai 1.7B is PrismML’s smallest Bonsai model, built for extremely fast on-device inference.… Text · Open weights 16 HF downloads
  4. GuppyLM Arman Hossain GuppyLM is a tiny open-source language model that roleplays as a fish named Guppy. It has about 8.7… Text · Open weights 12 HF downloads
  5. F pre 8kv 8k 14k SWA Ai2 F_pre_8kv_8k_14k_SWA is an AllenAI OlmPool architectural-variation model for studying long-context… Text · Open weights 6 HF downloads
  6. 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
  7. 1 Bit Bonsai 4B PrismML 1-bit Bonsai 4B is PrismML’s mid-size ultra-efficient model designed for fast local inference. It u… Text · Open weights Open weights
  8. 1 Bit Bonsai 8B PrismML 1-bit Bonsai 8B is PrismML’s flagship ultra-efficient language model, built with 1-bit weights for… Text · Open weights Open weights
  9. 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
  10. 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
  11. Baichuan 2 Baichuan Intelligent Technology Baichuan 2 is a next-generation open model series (7B and 13B) trained for stronger multilingual ge… Text · Open weights Open weights
  12. BGE base Beijing Academy of Artificial Intelligence (BAAI) BGE base is BAAI’s mid-size English BGE v1 embedding model. It is an encoder-only BERT-based text e… Text · Open weights Open weights
  13. BGE Base v1.5 Beijing Academy of Artificial Intelligence (BAAI) BGE Base v1.5 is BAAI’s mid-size English BGE v1.5 embedding model. It belongs to the Sep-2023 v1.5… Text · Open weights Open weights
  14. BGE ICL Beijing Academy of Artificial Intelligence (BAAI) BGE ICL is BAAI’s English embedding model with in-context learning. It is designed to improve retri… Text · Open weights Open weights
  15. BGE large v1.5 Beijing Academy of Artificial Intelligence (BAAI) BGE large v1.5 is BAAI’s top English BGE v1.5 embedding model. It is the large-scale Sep-2023 updat… Text · Open weights Open weights
  16. BGE small v1.5 Beijing Academy of Artificial Intelligence (BAAI) BGE small v1.5 is BAAI’s smallest English BGE v1.5 embedding model. It keeps the compact small-mode… Text · Open weights Open weights
  17. Celeris 1 Celeris Celeris-1 is Celeris Labs' debut model, a diffusion language model built for short, structured call… Text · Open weights Open weights
  18. Cerebras 8B Cerebras Systems Cerebras 8B is a compact general model for fast, low-cost chat, reasoning, and light coding that fi… Text · Open weights Open weights
  19. Chroma 1.0 Flash Labs FlashLabs Chroma 1.0 is a real-time spoken dialogue model that interleaves text and audio tokens to… Text · Open weights Open weights
  20. Chroma Context 1 Chroma Context-1 is Chroma’s 20B agentic search model trained as a self-editing search agent. It is design… Text · Open weights Open weights
  21. Code Llama Meta Platforms AI model by Meta Platforms Text · Open weights Open weights
  22. Coder DeepSeek AI model by DeepSeek Text · Open weights Open weights
  23. Codestral 25.01 Mistral AI Codestral 25.01 is Mistral’s code-specialized model, tuned for high-quality generation, completion… Text · Open weights Open weights
  24. Codestral Mamba Mistral AI Codestral Mamba is Mistral AI's 7.3B open-weight code model built on the Mamba2 state-space archite… Text · Open weights Open weights
  25. Command Cohere AI model by Cohere Text · Open weights Open weights
  26. Command A Caldera Labs Cohere Command A is an enterprise-grade instruction model built for reliable tool use, RAG, and mul… Text · Open weights Open weights
  27. Command R Caldera Labs Command R is Cohere’s retrieval-first model for long-context assistants. It is optimized for RAG, t… Text · Open weights Open weights
  28. Cosmos Nemotron VLM NVIDIA Cosmos Nemotron VLM is NVIDIA’s multimodal model that fuses Cosmos world-model perception with Nemo… Text · Open weights Open weights
  29. Deepseek 3.2 DeepSeek DeepSeek V3.2 is the core, stable 3.2-series model designed as a strong general-purpose LLM. It bui… Text · Open weights Open weights
  30. DeepSeek R1 Distill DeepSeek DeepSeek R1 Distill is a family of six small reasoning models released alongside DeepSeek R1, creat… Text · Open weights Open weights
  31. DeepSeek v2.5 DeepSeek AI model by DeepSeek Text · Open weights Open weights
  32. DeepSeek V3 DeepSeek AI model by DeepSeek Text · Open weights Open weights
  33. DeepSeek V3.1 Terminus DeepSeek DeepSeek-V3.1-Terminus is DeepSeek’s flagship reasoning model, tuned for difficult analysis, math,… Text · Open weights Open weights
  34. DeepSeek V3.2 Exp DeepSeek DeepSeek v3.2 Exp is an experimental build of the DeepSeek V3 line, tuned for deeper reasoning and… Text · Open weights Open weights
  35. DeepSeekMath V2 DeepSeek DeepSeek-Math-V2 is a math-specialized LLM built on DeepSeek-V3.2-Exp-Base, trained to generate and… Text · Open weights Open weights
  36. Devstral Small (24B) Mistral AI AI model by Mistral AI Text · Open weights Open weights