Blog Promote Sign in Sign up

Catalogs

Models

4,400 in the directory.

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

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
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. LingBot Video MoE Robbyant LingBot-Video-MoE is an open source Mixture-of-Experts video generation model with 30B total and 3B… Video · Open weights 15k HF downloads
  2. Nanbeige4.1 3B Nanbeige LLM Lab Nanbeige4.1-3B is a 3B-parameter reasoning model optimized to combine strong multi-step reasoning,… Text · Open weights 15k HF downloads
  3. Nemotron 3 Embed 1B NVFP4 NVIDIA Nemotron-3-Embed-1B-NVFP4 is a hardware accelerated, 8-bit quantized variant of NVIDIA's Nemotron-3… Text · Open weights 14k HF downloads
  4. Yi-6B 01.AI AI model by 01.AI Text · Open weights 14k HF downloads
  5. ZAYA1 8B Zyphra AI ZAYA1-8B is Zyphra’s small mixture-of-experts reasoning model, built for long-form reasoning, mathe… Multimodal · Closed 14k HF downloads
  6. LongCat Image Meituan 6B parameter bilingual (Chinese-English) text-to-image foundation model focused on photorealism, st… Image · Open weights 14k HF downloads
  7. SAM Audio Meta Platforms SAM Audio is Meta’s Segment Anything audio model, a unified system that segments sounds from comple… Audio · Open weights 14k HF downloads
  8. Hy4 preview Tencent Hy4 preview is a Mixture of Experts language model from Tencent with 770B total parameters, 49B act… Text · Open weights 14k HF downloads
  9. SenseNova U1 8B MoT SenseTime SenseNova-U1-8B-MoT is SenseNova’s open native multimodal model for unified image understanding, re… Multimodal · Open weights 13k HF downloads
  10. Phi 3 medium Microsoft Phi-3 Medium is Microsoft’s ~14B open-weight LLM tuned for strong instruction following, reasoning,… Text · Open weights 13k HF downloads
  11. Deep Live Cam Hacksider Deep-Live-Cam is a real-time face-swapping application for live camera and streaming-style video wo… Multimodal · Open weights 13k HF downloads
  12. Falcon Perception Technology Innovation Institute Falcon Perception is TII UAE’s 0.6B early-fusion vision-language model for open-vocabulary groundin… Multimodal · Open weights 13k HF downloads
  13. Nex N2.5 Max Nex-AGI A 1.6 trillion parameter Mixture of Experts text only agentic model built for long horizon tasks su… Text · Open weights 12k HF downloads
  14. North Mini Code 1.0 Cohere North Mini Code 1.0 is Cohere’s Apache 2.0 agentic coding model with 30B total parameters and 3B ac… Coding · Closed 12k HF downloads
  15. Phi 4 reasoning plus Microsoft Phi-4-reasoning-plus is an open-weight reasoning model derived from Phi-4, trained with chain-of-th… Text · Open weights 12k HF downloads
  16. Alpamayo R1 NVIDIA Alpamayo-R1 is NVIDIA's vision-language-action model for autonomous driving, combining Chain of Cau… Text · Open weights 12k HF downloads
  17. Shieldstral Mistral AI Shieldstral is a 3 billion parameter open weights multimodal safety classifier from Mistral AI. It… Structured data · Closed 12k HF downloads
  18. Wan2.2 I2V A14B Alibaba Wan2.2-I2V-A14B is an image-to-video model that animates a single frame or storyboard into a tempor… Video · Closed 12k HF downloads
  19. Claude Fable 5 Anthropic Claude Fable 5 is Anthropic’s generally available Mythos-class Claude model for frontier reasoning,… Multimodal · Closed 11k HF downloads
  20. Command R Plus Caldera Labs Command R+ is a higher-capability variant of Command R with stronger reasoning and coding while kee… Text · Open weights 11k HF downloads
  21. VibeThinker-1.5B WeiboAI VibeThinker-1.5B is WeiboAI’s compact instruction model designed for fast, cost-efficient assistant… Text · Open weights 11k HF downloads
  22. Apertus 8B 2509 Swiss AI Initiative Apertus 8B 2509 is a fully open 8B parameter language model by Swiss AI Initiative, pretrained on 1… Text · Open weights 11k HF downloads
  23. K2 Horizon 7B Institute of Foundation Models K2 Horizon 7B is a dense language model tuned for mobile and on device applications. It offers stro… Text · Open weights 11k HF downloads
  24. Wan2.2 S2V 14B Alibaba Wan2.2-S2V-14B is a speech-to-video model that turns a narrated prompt into a coherent, temporally… Video · Open weights 1k HF downloads
  25. Apodex 1.1 Apodex Apodex 1.1 is an agentic AI workbench that pairs reasoning with real execution across files, code,… Multimodal · Closed 1k HF downloads
  26. GLiNER2.5 Small V1 Fastino GLiNER2.5 Small is a 74M parameter span free information extraction model that predicts entity boun… Text · Open weights 9.9k HF downloads
  27. LFM2.5 1.2B Thinking Liquid AI LFM2.5-1.2B-Thinking is Liquid AI’s 1.2B parameter reasoning-focused variant of its LFM2.5 edge fam… Text · Open weights 9.7k HF downloads
  28. Command R7B Cohere Command R7B is Cohere's smallest and fastest model in the Command R family, with a 128K context win… Multimodal · Open weights 9.5k HF downloads
  29. GLM Image Z.ai GLM-Image is Z.ai's open-source auto-regressive plus diffusion image model for dense-knowledge, hig… Image · Open weights 9.5k HF downloads
  30. Stable Diffusion 3.5 Large Turbo Stability AI Speed-tuned variant of SD 3.5 Large that delivers near-final quality at much lower latency for rapi… Image · Open weights 9.1k HF downloads
  31. Cosmos Predict NVIDIA Cosmos Predict is NVIDIA’s generative world-model for forecasting what happens next. From short vid… Video · Open weights 9k HF downloads
  32. FLUX.2 [dev] Turbo Black Forest Labs FLUX.2 [dev] Turbo is Fal AI’s distilled Turbo LoRA for the FLUX.2-dev image model, cutting samplin… Image · Closed 8.7k HF downloads
  33. Magenta RealTime 2 Google DeepMind Magenta RealTime 2 is Google DeepMind’s open on-device live music-generation model for low-latency,… Audio · Closed 8.6k HF downloads
  34. Rampart National Design Studio Rampart is a 14.7 MB quantized ONNX token-classification model for client-side PII detection and re… Text · Closed 8.4k HF downloads
  35. K2 Horizon 3.7B Institute of Foundation Models K2 Horizon 3.7B is a dense language model aimed at developers and researchers who want to fine tune… Text · Open weights 7.7k HF downloads
  36. PaddleOCR-VL Baidu PaddleOCR-VL is a vision-language model built around PaddleOCR that reads documents, forms, tables,… Multimodal · Closed 7.6k HF downloads