Promote Sign in Sign up

Catalogs

Models

761 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
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. Nemotron-Orchestrator-8B-GGUF MaziyarPanahi text generation · 86,108 downloads · by MaziyarPanahi Text · Open weights 86k HF downloads
  2. Trinity-Mini-GGUF MaziyarPanahi text generation · License apache-2.0 · 86,023 downloads · by MaziyarPanahi Text · Open weights 86k HF downloads
  3. Qwen3-1.7B-GGUF Qwen text generation · License apache-2.0 · 85,522 downloads · by Qwen Text · Open weights 86k HF downloads
  4. needle3 Cactus-Compute text generation · License apache-2.0 · 85,362 downloads · by Cactus-Compute Text · Open weights 85k HF downloads
  5. Qwen2.5-72B-Instruct-GGUF bartowski text generation · License other · 85,310 downloads · by bartowski Text · Open weights 85k HF downloads
  6. Dream-v0-Instruct-7B Dream-org text generation · License apache-2.0 · 84,953 downloads · by Dream-org Text · Open weights 85k HF downloads
  7. Qwen1.5-7B Qwen text generation · License other · 84,750 downloads · by Qwen Text · Open weights 85k HF downloads
  8. Qwen2.5-Coder-7B-Instruct-bnb-4bit unsloth text generation · License apache-2.0 · 84,356 downloads · by unsloth Text · Open weights 84k HF downloads
  9. Qwen3-Coder-30B-A3B-Instruct-GGUF lmstudio-community text generation · 84,135 downloads · by lmstudio-community Text · Open weights 84k HF downloads
  10. Qwen2.5-Math-7B-Instruct Qwen text generation · License apache-2.0 · 83,261 downloads · by Qwen Text · Open weights 83k HF downloads
  11. Meta-Llama-3.1-8B-Instruct unsloth text generation · License llama3.1 · 205,919 downloads · by unsloth Text · Open weights 83k HF downloads
  12. LFM2.5 230M Liquid AI LFM2.5-230M is a 230M-parameter lightweight language model built on the LFM2 architecture, designed… Text · Open weights 83k HF downloads
  13. TinyLLama-v0 Maykeye text generation · License apache-2.0 · 82,853 downloads · by Maykeye Text · Open weights 83k HF downloads
  14. LFM2.5-1.2B-Instruct-MLX-8bit lmstudio-community text generation · License other · 82,618 downloads · by lmstudio-community Text · Open weights 83k HF downloads
  15. opt-125m optimum-intel-internal-testing text generation · License other · 82,603 downloads · by optimum-intel-internal-testing Text · Open weights 83k HF downloads
  16. Meta-Llama-3.1-8B-Instruct-GGUF lmstudio-community text generation · License llama3.1 · 82,466 downloads · by lmstudio-community Text · Open weights 82k HF downloads
  17. DeepSeek-R1-0528-Qwen3-8B-GGUF lmstudio-community text generation · License mit · 82,446 downloads · by lmstudio-community Text · Open weights 82k HF downloads
  18. tiny-GPTNeoXForCausalLM trl-internal-testing text generation · 82,392 downloads · by trl-internal-testing Text · Open weights 82k HF downloads
  19. Qwen3-30B-A3B-GGUF Qwen text generation · License apache-2.0 · 82,235 downloads · by Qwen Text · Open weights 82k HF downloads
  20. gpt2-xl openai-community text generation · License mit · 81,519 downloads · by openai-community Text · Open weights 82k HF downloads
  21. 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
  22. 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
  23. 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
  24. 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
  25. 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
  26. 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
  27. GPT OSS Safeguard OpenAI GPT OSS Safeguard is a safety and policy companion model. It classifies risk, explains the rational… Text · Closed 55k HF downloads
  28. 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
  29. GPT-Neo EleutherAI AI model by EleutherAI Text · Closed 45k HF downloads
  30. Edge0-35B Edge0 Edge0-35B is a 35 billion parameter sparse mixture of experts language model built on Qwen3.5-MoE 3… Text · Closed 37k HF downloads
  31. HRM Text 1B Sapient Intelligence HRM-Text-1B is Sapient Intelligence’s open-source 1B-parameter text-generation language model built… Text · Closed 28k HF downloads
  32. 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
  33. 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
  34. 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
  35. 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
  36. 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