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. tiny-GPTNeoXForCausalLM trl-internal-testing text generation · 82,392 downloads · by trl-internal-testing Text · Open weights 82k HF downloads
  2. jina-clip-v1 jinaai feature extraction · License apache-2.0 · 82,307 downloads · by jinaai Text · Open weights 82k HF downloads
  3. bartpho-syllable vinai feature extraction · License mit · 82,235 downloads · by vinai Text · Open weights 82k HF downloads
  4. Qwen3-30B-A3B-GGUF Qwen text generation · License apache-2.0 · 82,235 downloads · by Qwen Text · Open weights 82k HF downloads
  5. bert-kor-base kykim fill mask · 81,948 downloads · by kykim Text · Open weights 82k HF downloads
  6. bart-large-cnn-samsum philschmid summarization · License mit · 81,722 downloads · by philschmid Text · Open weights 82k HF downloads
  7. sentence-bert-base-ja-mean-tokens-v2 sonoisa feature extraction · License cc-by-sa-4.0 · 81,639 downloads · by sonoisa Text · Open weights 82k HF downloads
  8. OpenMed-PII-SuperClinical-Large-434M-v1 OpenMed token classification · License apache-2.0 · 81,581 downloads · by OpenMed Text · Open weights 82k HF downloads
  9. gpt2-xl openai-community text generation · License mit · 81,519 downloads · by openai-community Text · Open weights 82k HF downloads
  10. Granite 4.2 IBM Granite 4.2 is a family of dense language models from IBM available in 3B, 8B, and 30B parameter si… Text · Open weights 78k HF downloads
  11. QwQ 32B Alibaba QwQ 32B is Alibaba's open-weight reasoning model, a 32.5B dense transformer trained with large-scal… Text · Open weights 77k HF downloads
  12. Nemotron 3 Super NVIDIA Nemotron 3 Super is NVIDIA’s open Mixture-of-Experts hybrid Mamba-Transformer model designed for hi… Text · Open weights 77k HF downloads
  13. Magistral Small Mistral AI Magistral Small is a compact model from Mistral’s specialized lineup, tuned for efficiency while st… Text · Open weights 74k HF downloads
  14. ChatGLM3 Tsinghua University AI model by Tsinghua University Text · Open weights 68k HF downloads
  15. Phi 3 vision Gentext Group Phi-3-Vision is Microsoft’s compact, open-weight multimodal model that understands images + text an… Text · Open weights 68k HF downloads
  16. Llama Guard 3 Meta Platforms Llama Guard 3 is Meta’s open-weight safety model for moderating AI prompts and responses. It classi… Text · Open weights 59k HF downloads
  17. LightOnOCR 1B LightOn LightOnOCR-1B is a compact vision-language model for OCR that converts document images into clean t… Text · Open weights 56k HF downloads
  18. Kimi K2 Thinking Moonshot AI Kimi K2 Thinking is Moonshot AI’s open-source reasoning-oriented K2 variant, built for deep multi-s… Text · Open weights 55k HF downloads
  19. Phi 4 mini reasoning Microsoft Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-qua… Text · Open weights 55k HF downloads
  20. Llama 4 Maverick Meta Platforms AI model by Meta Platforms Text · Open weights 52k HF downloads
  21. Pplx Embed Perplexity pplx-embed is a family of text embedding models built for real-world, web-scale retrieval. Text · Open weights 51k HF downloads
  22. pplx embed v1 0.6b Perplexity A 0.6B parameter multilingual text embedding model built on a diffusion-pretrained Qwen3 backbone.… Text · Open weights 51k HF downloads
  23. MiniMax VL 01 MiniMax MiniMax-VL-01 is a vision-language model that reads images and text together. It handles OCR, chart… Text · Open weights 29k HF downloads
  24. LFM2 VL 3B Liquid AI LFM2-VL-3B is a 3B vision-language model that reads images with text and answers in natural languag… Text · Open weights 29k HF downloads
  25. Hy-MT2 Tencent Hy-MT2 is Tencent Hunyuan’s open-source multilingual translation model family for fast-thinking, in… Text · Open weights 29k HF downloads
  26. GLiNER2.5 Base V1 Fastino GLiNER2.5 Base is a 0.2B parameter span free information extraction model that predicts entity boun… Text · Open weights 28k HF downloads
  27. MiniMax M2.1 MiniMax MiniMax M2.1 is MiniMax’s open-source sparse MoE coding and agent model, with about 10B active para… Text · Open weights 27k HF downloads
  28. Trinity Mini Arcee AI Trinity Mini is a 26B-parameter (3B active) Trinity MoE model with 128K context, tuned for strong r… Text · Open weights 27k HF downloads
  29. Baichuan 7B Baichuan Intelligent Technology Baichuan-7B is a bilingual Chinese-English 7B-parameter pretrained language model built for general… Text · Open weights 25k HF downloads
  30. Phi 3 small Microsoft Phi-3 Small is Microsoft’s ~7B open-weight LLM tuned for instruction following, reasoning, and codi… Text · Open weights 24k HF downloads
  31. LongCat Flash Chat Meituan Chat-oriented LongCat-Flash variant, a 560B MoE language model with around 27B parameters active pe… Text · Open weights 24k HF downloads
  32. Ministral 3B Mistral AI Ministral 3B (2410) is Mistral’s ultra-compact dense LLM—around 3 billion parameters—built for spee… Text · Open weights 23k HF downloads
  33. LFM2.5 Embedding 350M Liquid AI 350M-parameter bidirectional multilingual bi-encoder that maps each document to a single dense vect… Text · Open weights 23k HF downloads
  34. Apertus 70B Instruct 2509 Swiss AI Initiative Apertus 70B Instruct is a fully open 70B-parameter decoder-only language model trained from scratch… Text · Open weights 22k HF downloads
  35. Granite 4.0 1B IBM Granite-4.0-1B is IBM’s lightweight instruction model built for efficient agentic tasks like instru… Text · Open weights 21k HF downloads
  36. Nemotron Cascade 2 30B A3B NVIDIA Nemotron-Cascade 2 is an open 30B Mixture-of-Experts model (3B activated) trained with Cascade RL a… Text · Open weights 21k HF downloads