Blog Promote Sign in Sign up

Catalogs

Models

3,241 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. Pplx Embed Perplexity pplx-embed is a family of text embedding models built for real-world, web-scale retrieval. Text · Open weights 51k HF downloads
  2. pplx embed v1 0.6b Perplexity A 0.6B parameter multilingual text embedding model built on a diffusion-pretrained Qwen3 backbone.… Text · Open weights 51k HF downloads
  3. LFM2.5 VL 450M Liquid AI LFM2.5-VL-450M is Liquid AI’s compact vision-language model for structured visual intelligence from… Image · Open weights 46k HF downloads
  4. GLM 4.5V Z.ai GLM-4.5V is a 106B parameter (12B active) MoE-based visual reasoning model supporting image, video,… Multimodal · Open weights 46k HF downloads
  5. Cohere Transcribe Arabic Cohere Cohere Transcribe Arabic is a 2B parameter conformer based encoder decoder automatic speech recogni… Audio · Open weights 44k HF downloads
  6. Canary 1B v2 NVIDIA Multilingual, multitask speech recognition model (ASR) in the NVIDIA NeMo family. Audio · Open weights 39k HF downloads
  7. InfiniteTalk MeiGen AI InfiniteTalk is a sparse-frame audio-driven video generation model that synthesizes video with sync… Video · Open weights 38k HF downloads
  8. Qwen AgentWorld 35B A3B Alibaba Qwen-AgentWorld-35B-A3B is a 35B Mixture-of-Experts language world model with 3B active parameters,… Multimodal · Open weights 33k HF downloads
  9. Nex N2.5 Pro Nex-AGI A multimodal agentic model trained to operate computers and browsers directly and to autonomously r… Multimodal · Open weights 31k HF downloads
  10. MiniMax VL 01 MiniMax MiniMax-VL-01 is a vision-language model that reads images and text together. It handles OCR, chart… Text · Open weights 29k HF downloads
  11. Dia 1.6B Nari Labs Dia-1.6B is Nari Labs’ ultra-compact instruction model—about 1.6B parameters—built for fast, low-co… Audio · Open weights 29k HF downloads
  12. LFM2 VL 3B Liquid AI LFM2-VL-3B is a 3B vision-language model that reads images with text and answers in natural languag… Text · Open weights 29k HF downloads
  13. Hy-MT2 Tencent Hy-MT2 is Tencent Hunyuan’s open-source multilingual translation model family for fast-thinking, in… Text · Open weights 29k HF downloads
  14. GLiNER2.5 Base V1 Fastino GLiNER2.5 Base is a 0.2B parameter span free information extraction model that predicts entity boun… Text · Open weights 28k HF downloads
  15. Mage VL Microsoft Mage-VL is a 4B-parameter multimodal model for image and video understanding, built on a from-scrat… Multimodal · Open weights 27k HF downloads
  16. 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
  17. 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
  18. Intern S1 InternLM Intern-S1 is a scientific multimodal foundation model built on a 235B-parameter Qwen3 MoE LLM plus… Multimodal · Open weights 26k HF downloads
  19. Antares 1B Cisco Systems Antares 1B is a compact security-focused language model from Cisco for locating vulnerable source f… Coding · Open weights 25k HF downloads
  20. 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
  21. 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
  22. 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
  23. Ministral 3B Mistral AI Ministral 3B (2410) is Mistral’s ultra-compact dense LLM—around 3 billion parameters—built for spee… Text · Open weights 23k HF downloads
  24. LFM2.5 Embedding 350M Liquid AI 350M-parameter bidirectional multilingual bi-encoder that maps each document to a single dense vect… Text · Open weights 23k HF downloads
  25. Apertus 70B Instruct 2509 Swiss AI Initiative Apertus 70B Instruct is a fully open 70B-parameter decoder-only language model trained from scratch… Text · Open weights 22k HF downloads
  26. Granite 4.0 1B IBM Granite-4.0-1B is IBM’s lightweight instruction model built for efficient agentic tasks like instru… Text · Open weights 21k HF downloads
  27. Nemotron Cascade 2 30B A3B NVIDIA Nemotron-Cascade 2 is an open 30B Mixture-of-Experts model (3B activated) trained with Cascade RL a… Text · Open weights 21k HF downloads
  28. Nemotron Labs Diffusion 14B NVIDIA Nemotron-Labs-Diffusion-14B is NVIDIA’s open 14B text-generation language model that supports autor… Text · Open weights 21k HF downloads
  29. K2 Horizon 0.9B Institute of Foundation Models K2 Horizon 0.9B is a compact dense language model designed for highly constrained environments such… Text · Open weights 2k HF downloads
  30. Lens Microsoft Microsoft Lens is an open-source 3.8B text-to-image model focused on efficient training, fast high-… Multimodal · Open weights 2k HF downloads
  31. Nanbeige4.2-3B Nanbeige LLM Lab Nanbeige4.2-3B is a compact 3B-parameter agentic language model using a Looped Transformer architec… Text · Open weights 2k HF downloads
  32. GLM 4.6 Z.ai GLM 4.6 is Zhipu AI’s newest general-purpose model, improving on 4.5 with steadier reasoning, stron… Text · Open weights 19k HF downloads
  33. Ming Omni InclusionAI Ming-Omni is an end-to-end multimodal assistant that reads text, images, audio, and video, then rep… Multimodal · Open weights 19k HF downloads
  34. Command A Vision Caldera Labs Command A Vision is Cohere’s multimodal instruction model that pairs text and image understanding.… Text · Open weights 19k HF downloads
  35. HunyuanImage 3.0 Instruct Tencent HunyuanImage-3.0-Instruct is Tencent’s 80B MoE image-editing model that first reasons over an input… Image · Open weights 18k HF downloads
  36. LingBot World Fast Robbyant LingBot World Fast is an open source image to video world model that generates long, temporally con… Video · Open weights 18k HF downloads