Catalogs

Models

885 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

Weights and source
Explore other catalogs
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. Qwen3-VL-8B-Instruct Qwen image text to text · License apache-2.0 · 18,014,795 downloads · by Qwen Multimodal · Open weights 18M HF downloads
  2. gemma-4-26B-A4B-it google image text to text · License apache-2.0 · 11,784,225 downloads · by google Multimodal · Open weights 12M HF downloads
  3. Krea 2 Krea.ai Krea 2 is Krea AI’s real-time generative image model for highly controllable visual creation and ed… Multimodal · Open weights 9.9M HF downloads
  4. Qwen 3.5 9B Alibaba Qwen3.5-9B is a larger dense vision-language causal model with a vision encoder, targeting stronger… Multimodal · Open weights 9.9M HF downloads
  5. Qwen 3.5 4B Alibaba Qwen3.5-4B is a mid-size vision-language causal model with a vision encoder, designed for multimoda… Multimodal · Open weights 7.1M HF downloads
  6. Qwen3.8-27B Alibaba Qwen3.8-27B is a 27B-parameter dense vision-language model from the Qwen3.8 series, built on the Qw… Multimodal · Open weights 6.7M HF downloads
  7. Qwen2.5-VL-7B-Instruct Qwen image text to text · License apache-2.0 · 6,300,275 downloads · by Qwen Multimodal · Open weights 6.3M HF downloads
  8. Qwen3.8-27B-FP8 Qwen image text to text · License apache-2.0 · 5,322,914 downloads · by Qwen Multimodal · Open weights 5.3M HF downloads
  9. Qwen 3.5 2B Alibaba Qwen3.5-2B is a small vision-language causal model with a vision encoder, aimed at strong multimoda… Multimodal · Open weights 4.9M HF downloads
  10. Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF cdiamond image text to text · License apache-2.0 · 4,707,156 downloads · by cdiamond Multimodal · Open weights 4.7M HF downloads
  11. Qwen3.8-27B-MLX-4bit lmstudio-community image text to text · License apache-2.0 · 4,431,061 downloads · by lmstudio-community Multimodal · Open weights 4.4M HF downloads
  12. GLM 5.3 Flash Z.ai GLM 5.3 Flash is a natively multimodal mixture of experts language model with 320B total parameters… Multimodal · Open weights 4.3M HF downloads
  13. Qwen3.8-27B-MLX-8bit lmstudio-community image text to text · License apache-2.0 · 4,239,070 downloads · by lmstudio-community Multimodal · Open weights 4.2M HF downloads
  14. Qwen3.8-27B-MLX-6bit lmstudio-community image text to text · License apache-2.0 · 4,207,386 downloads · by lmstudio-community Multimodal · Open weights 4.2M HF downloads
  15. Qwen3.8-27B-MLX-5bit lmstudio-community image text to text · License apache-2.0 · 4,188,542 downloads · by lmstudio-community Multimodal · Open weights 4.2M HF downloads
  16. Qwen 3.6 27B Alibaba Qwen3.6-27B is Qwen’s open-weight multimodal model for coding, agent workflows, long-context reason… Multimodal · Open weights 3.8M HF downloads
  17. MiniMax H3 MiniMax MiniMax H3 is a general purpose omni modal generation model that jointly understands multimodal con… Multimodal · Open weights 3.7M HF downloads
  18. Stable Diffusion XL Stability AI Stable Diffusion XL is a larger two-stage SD model that delivers richer color, better prompt fideli… Multimodal · Open weights 3.7M HF downloads
  19. Qwen 3.6 35B A3B Alibaba Qwen3.6-35B-A3B is Qwen’s open-weight multimodal MoE model for coding, agentic workflows, long-cont… Multimodal · Open weights 3.5M HF downloads
  20. Qwen3-VL-4B-Instruct Qwen image text to text · License apache-2.0 · 3,425,252 downloads · by Qwen Multimodal · Open weights 3.4M HF downloads
  21. Qwen3.6-35B-A3B-FP8 Qwen image text to text · License apache-2.0 · 7,638,786 downloads · by Qwen Multimodal · Open weights 3.3M HF downloads
  22. Florence 2 Microsoft Florence 2 is Microsoft's compact vision foundation model, released at 232M and 771M parameters und… Multimodal · Open weights 3M HF downloads
  23. Qwen3-VL-2B-Instruct Qwen image text to text · License apache-2.0 · 2,916,540 downloads · by Qwen Multimodal · Open weights 2.9M HF downloads
  24. Qwen3.6-27B-FP8 Qwen image text to text · License apache-2.0 · 4,490,074 downloads · by Qwen Multimodal · Open weights 2.7M HF downloads
  25. Qwen 3.5 0.8B Alibaba Qwen3.5-0.8B is a compact vision-language causal model with a vision encoder, built for multimodal… Multimodal · Open weights 2.5M HF downloads
  26. Qwen2.5-VL-3B-Instruct Qwen image text to text · 2,348,120 downloads · by Qwen Multimodal · Open weights 2.3M HF downloads
  27. Chandra OCR 2 Datalab Chandra is an OCR model for difficult document extraction tasks. Its GitHub description says it han… Multimodal · Open weights 2.3M HF downloads
  28. Huihui-Qwen3.8-27B-abliterated-GGUF huihui-ai image text to text · License apache-2.0 · 2,201,683 downloads · by huihui-ai Multimodal · Open weights 2.2M HF downloads
  29. DeepSeek OCR DeepSeek LLM-centric OCR model using “Contexts Optical Compression” to explore visual-text compression and p… Multimodal · Open weights 2.2M HF downloads
  30. Qwen3-VL-8B-Instruct-FP8 Qwen image text to text · License apache-2.0 · 2,065,600 downloads · by Qwen Multimodal · Open weights 2.1M HF downloads
  31. Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF HauhauCS image text to text · License apache-2.0 · 2,044,324 downloads · by HauhauCS Multimodal · Open weights 2M HF downloads
  32. gemma-4-12B-it google any to any · License apache-2.0 · 1,977,870 downloads · by google Multimodal · Open weights 2M HF downloads
  33. Qwen2-VL-2B-Instruct Qwen image text to text · License apache-2.0 · 1,967,043 downloads · by Qwen Multimodal · Open weights 2M HF downloads
  34. moondream2 vikhyatk image text to text · License apache-2.0 · 1,961,708 downloads · by vikhyatk Multimodal · Open weights 2M HF downloads
  35. Unlimited-OCR baidu image text to text · License mit · 1,826,036 downloads · by baidu Multimodal · Open weights 1.8M HF downloads
  36. Qwen3.5-27B Qwen image text to text · License apache-2.0 · 1,824,362 downloads · by Qwen Multimodal · Open weights 1.8M HF downloads