Promote Sign in Sign up

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

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. InternVL2-1B OpenGVLab image text to text · License mit · 703,603 downloads · by OpenGVLab Multimodal · Open weights 704k HF downloads
  2. Cosmos Reason NVIDIA Cosmos Reason is NVIDIA’s open, customizable 7B-parameter reasoning VLM for physical AI and robotic… Multimodal · Open weights 695k HF downloads
  3. HunyuanOCR Tencent HunyuanOCR is Tencent Hunyuan’s 1B parameter end-to-end OCR expert VLM. It reads documents, screens… Multimodal · Open weights 692k HF downloads
  4. Flux.1 Dev Black Forest Labs AI model by Black Forest Labs Multimodal · Open weights 682k HF downloads
  5. InternVL2-2B OpenGVLab image text to text · License mit · 680,219 downloads · by OpenGVLab Multimodal · Open weights 68k HF downloads
  6. stable-diffusion-v1-4 CompVis text to image · License creativeml-openrail-m · 666,628 downloads · by CompVis Multimodal · Open weights 667k HF downloads
  7. gemma-4-31B-it google image text to text · License apache-2.0 · 9,460,570 downloads · by google Multimodal · Open weights 66k HF downloads
  8. DeepSeek V4.1 Flash DeepSeek DeepSeek V4.1 Flash is a 552B parameter multimodal mixture of experts model with 8B active paramete… Multimodal · Open weights 651k HF downloads
  9. XYZAILab_XYZ-Aquila-mini-GGUF bartowski image text to text · License apache-2.0 · 647,862 downloads · by bartowski Multimodal · Open weights 648k HF downloads
  10. Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF DavidAU image text to text · License apache-2.0 · 636,230 downloads · by DavidAU Multimodal · Open weights 636k HF downloads
  11. Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 nvidia any to any · License other · 628,059 downloads · by nvidia Multimodal · Open weights 628k HF downloads
  12. Inkling Small Thinking Machines Lab Inkling Small is an open weights Mixture of Experts transformer from Thinking Machines Lab with 276… Multimodal · Open weights 623k HF downloads
  13. llava-onevision-qwen2-0.5b-ov-hf llava-hf image text to text · License apache-2.0 · 618,675 downloads · by llava-hf Multimodal · Open weights 619k HF downloads
  14. Pixal3D Tencent Pixal3D is Tencent ARC Lab and collaborators’ image-to-3D generation model for creating high-fideli… Multimodal · Open weights 615k HF downloads
  15. DiffusionGemma Google DiffusionGemma is Google’s open experimental 26B MoE text-diffusion model for faster local text gen… Multimodal · Open weights 613k HF downloads
  16. gemma-4-26B-A4B-it-qat-GGUF unsloth image text to text · License apache-2.0 · 612,713 downloads · by unsloth Multimodal · Open weights 613k HF downloads
  17. Qwen3.5-9B-MLX-4bit lmstudio-community image text to text · License apache-2.0 · 610,770 downloads · by lmstudio-community Multimodal · Open weights 611k HF downloads
  18. PP-OCRv5_server_det PaddlePaddle image to text · License apache-2.0 · 610,613 downloads · by PaddlePaddle Multimodal · Open weights 611k HF downloads
  19. Inkling Thinking Machines Lab Inkling is an open-weights Mixture-of-Experts transformer from Thinking Machines Lab with 975B tota… Multimodal · Open weights 608k HF downloads
  20. gemma-4-E4B-it-GGUF unsloth image text to text · License apache-2.0 · 603,554 downloads · by unsloth Multimodal · Open weights 604k HF downloads
  21. GOT-OCR2_0 stepfun-ai image text to text · License apache-2.0 · 603,307 downloads · by stepfun-ai Multimodal · Open weights 603k HF downloads
  22. Qwen3-VL-8B-Instruct-AWQ-4bit cyankiwi image text to text · License apache-2.0 · 601,087 downloads · by cyankiwi Multimodal · Open weights 601k HF downloads
  23. Z-Image-Turbo Tongyi-MAI text to image · License apache-2.0 · 597,898 downloads · by Tongyi-MAI Multimodal · Open weights 598k HF downloads
  24. UI-TARS-1.5-7B ByteDance-Seed image text to text · License apache-2.0 · 594,892 downloads · by ByteDance-Seed Multimodal · Open weights 595k HF downloads
  25. Deepseek V4 Pro DeepSeek DeepSeek-V4-Pro is DeepSeek’s new flagship open-source model for top-end reasoning, coding, world k… Multimodal · Open weights 594k HF downloads
  26. Qwen3-Omni-30B-A3B-Instruct Qwen any to any · License other · 582,189 downloads · by Qwen Multimodal · Open weights 582k HF downloads
  27. tiny-Qwen2_5_VLForConditionalGeneration trl-internal-testing image text to text · 579,388 downloads · by trl-internal-testing Multimodal · Open weights 579k HF downloads
  28. blip-image-captioning-large Salesforce image to text · License bsd-3-clause · 574,113 downloads · by Salesforce Multimodal · Open weights 574k HF downloads
  29. gemma-4-E4B-it-qat-GGUF unsloth any to any · License apache-2.0 · 570,025 downloads · by unsloth Multimodal · Open weights 57k HF downloads
  30. gemma-4-E4B-it google any to any · License apache-2.0 · 4,419,050 downloads · by google Multimodal · Open weights 568k HF downloads
  31. Qwen3.5-9B-MLX-8bit lmstudio-community image text to text · License apache-2.0 · 567,941 downloads · by lmstudio-community Multimodal · Open weights 568k HF downloads
  32. inkling-GGUF unsloth image text to text · License apache-2.0 · 564,334 downloads · by unsloth Multimodal · Open weights 564k HF downloads
  33. gemma-4-26B-A4B-it-GGUF unsloth image text to text · License apache-2.0 · 555,341 downloads · by unsloth Multimodal · Open weights 555k HF downloads
  34. gemma-3-12b-it google image text to text · License gemma · 548,243 downloads · by google Multimodal · Open weights 548k HF downloads
  35. Qwythos-9B-v2-GGUF empero-ai image text to text · License apache-2.0 · 542,566 downloads · by empero-ai Multimodal · Open weights 543k HF downloads
  36. gemma-4-E2B-it-qat-q4_0-gguf google any to any · License apache-2.0 · 540,200 downloads · by google Multimodal · Open weights 54k HF downloads