Blog Promote Sign in Sign up

Catalogs

Models

3,545 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. Krea Realtime Krea.ai Krea Realtime is a live generative image engine that updates as you type, draw, or use a camera. It… Video · Open weights 5.4k HF downloads
  2. pplx embed context v1 0.6b Perplexity A 0.6B-parameter contextual text embedding model for RAG pipelines. Unlike standard embedding model… Text · Open weights 5.2k HF downloads
  3. DeepSeek 3.2 Speciale DeepSeek DeepSeek-V3.2-Speciale is a 685B-parameter research-only variant of DeepSeek-V3.2 that pushes open-… Text · Open weights 5.2k HF downloads
  4. Marlin 2B NemoStation Marlin-2B is NemoStation’s open-source 2B video-language model for dense video captioning and natur… Multimodal · Open weights 5k HF downloads
  5. LFM2.5 ColBERT 350M Liquid AI 350M-parameter bidirectional multilingual retrieval model using per-token ColBERT-style late intera… Text · Open weights 4.7k HF downloads
  6. GLM 4.6V Z.ai Open-source multimodal model series with native function calling. Available in 106B (cloud) and 9B… Multimodal · Open weights 4.4k HF downloads
  7. HunyuanWorld Mirror Tencent HunyuanWorld Mirror is a scene-reconstruction and world-modeling system. It turns photos and videos… Image · Open weights 4.3k HF downloads
  8. Trinity Large Thinking Arcee AI Trinity-Large-Thinking is Arcee AI’s open-source reasoning model for long-horizon agents and multi-… Text · Open weights 4.3k HF downloads
  9. Step-Audio-EditX StepFun Step-Audio-EditX is a text-guided audio editor for speech, music, and effects. Describe the change… Audio · Open weights 4.1k HF downloads
  10. Ternary Bonsai 27B AWQ 4bit PrismML Ternary Bonsai 27B AWQ 4bit is a 4 bit AWQ quantized build of PrismML's Ternary Bonsai 27B, a multi… Multimodal · Open weights 4k HF downloads
  11. Snowflake Arctic Instruct Snowflake Snowflake Arctic Instruct is an instruction-tuned Arctic model built on Snowflake’s dense-MoE hybri… Text · Open weights 3.9k HF downloads
  12. BGE Reranker v2 minicpm layerwise Beijing Academy of Artificial Intelligence (BAAI) BGE Reranker v2 minicpm layerwise is BAAI’s layer-selectable multilingual reranker in the v2 family… Text · Open weights 3.9k HF downloads
  13. Ring 2.5 1T InclusionAI Trillion-parameter “thinking” model described as using a hybrid linear attention architecture for l… Text · Open weights 3.9k HF downloads
  14. LFM2 24B A2B Liquid AI LFM2-24B-A2B is a hybrid Mixture-of-Experts language model designed for efficient on-device deploym… Text · Open weights 3.8k HF downloads
  15. pplx embed context v1 4B Perplexity A 4B-parameter contextual text embedding model built on diffusion-pretrained Qwen3, designed for RA… Text · Open weights 3.7k HF downloads
  16. HY World 2.0 Tencent HY-World 2.0 is Tencent Hunyuan’s multimodal 3D world model for reconstructing, generating, and sim… Multimodal · Open weights 3.7k HF downloads
  17. NVIDIA NemotronLabs VoiceChat 11B NVIDIA NVIDIA NemotronLabs VoiceChat 11B is NVIDIA’s open full-duplex speech-to-speech model for real-time… Multimodal · Open weights 3.5k HF downloads
  18. Instella MoE 16B A3B Think AMD Instella-MoE-16B-A3B-Think is the final reinforcement-learning tuned checkpoint of AMD's Instella-M… Text · Open weights 3.2k HF downloads
  19. Apriel 1.5 15B Thinker ServiceNow Apriel-1.5-15B-Thinker is a 15B multimodal reasoning model from ServiceNow, delivering frontier-lev… Text · Open weights 3.2k HF downloads
  20. HunyuanImage 3.0 Tencent HunyuanImage 3.0 is Tencent’s next-gen text-to-image model. It delivers sharper detail, stronger st… Image · Open weights 3.1k HF downloads
  21. Hermes 4.3 Nous Research Hermes 4.3 is Nous Research’s 36B hybrid reasoning model, based on Seed-OSS-36B, offering long cont… Text · Open weights 3.1k HF downloads
  22. Ling-1T AntGroup Ling 1T is the flagship model in the Ling family. It targets high-accuracy reasoning, coding, and m… Text · Open weights 3.1k HF downloads
  23. K2 Horizon 32B Institute of Foundation Models K2 Horizon 32B is a dense language model built for local hosting on laptops and on premise servers.… Text · Open weights 3.1k HF downloads
  24. Hunyuan-MT-7B Tencent Hunyuan-MT-7B is Tencent’s compact 7B multilingual model tuned for fast, accurate translation and c… Text · Open weights 3.1k HF downloads
  25. AuK Tencent AuK is a 1.5 billion parameter open source speech foundation model that generates and edits speech… Audio · Open weights 3k HF downloads
  26. Canary 180m flash NVIDIA Canary 180M Flash is a compact automatic speech recognition model in NVIDIA’s Canary family, design… Audio · Open weights 3k HF downloads
  27. Hunyuan3D-Omni Tencent AI model by Tencent 3D · Open weights 2.9k HF downloads
  28. Ling flash 2.0 AntGroup Ling-flash-2.0 is a high-speed multilingual instruction model built for very low latency and high t… Text · Open weights 2.7k HF downloads
  29. HiDream O1 Image Dev HiDream.ai HiDream O1 Image Dev is fal’s developer-focused image generation model for high-quality visual synt… Multimodal · Open weights 2.7k HF downloads
  30. EVIE-Preview-4.5B Tencent EVIE-Preview-4.5B is a multilingual visual document retrieval model built on the Qwen3.5-4B vision… Multimodal · Open weights 2.6k HF downloads
  31. Orchestrator-8B NVIDIA ToolOrchestra is NVIDIA’s method for training small “orchestrator” models that decide when and how… Text · Open weights 2.6k HF downloads
  32. Huihui granite 4.1 3b abliterated HuiHui ai Huihui-granite-4.1-3b-abliterated is a community-modified version of IBM’s Granite 4.1 3B model, bu… Text · Open weights 2.4k HF downloads
  33. Mistral Large Mistral AI AI model by Mistral AI Text · Open weights 2.4k HF downloads
  34. LLaDA2.0 Uni AntGroup LLaDA2.0-Uni is Inclusion AI’s unified multimodal diffusion MoE model for both image understanding… Text · Open weights 2.4k HF downloads
  35. Ling 2.6 flash AntGroup Ling-2.6-Flash is Ant Ling’s high-efficiency instruct language model, built for strong real-agent p… Text · Open weights 2.3k HF downloads
  36. Maple-Preview DeepGrove Maple-Preview is a 20B-parameter mixture-of-experts language model using ternary weights, built for… Text · Open weights 2.2k HF downloads