Promote Sign in Sign up

Catalogs

Models

793 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. 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
  2. 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
  3. 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
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. Falcon-40B Technology Innovation Institute AI model by Technology Innovation Institute Text · Open weights 7.5k HF downloads
  10. Nex N2.5 mini Nex-AGI A 35 billion parameter Mixture of Experts multimodal agentic model that operates computers and brow… Multimodal · Open weights 7.3k HF downloads
  11. HyperCLOVA X SEED Vision Naver HyperCLOVA X SEED Vision (3B) is NAVER’s lightweight multimodal model capable of understanding imag… Text · Closed 6.8k HF downloads
  12. K2 Horizon 375B A23B Institute of Foundation Models K2 Horizon 375B A23B is a sparse mixture of experts language model with 375 billion total parameter… Text · Open weights 5.9k HF downloads
  13. Ling mini 2.0 AntGroup Ling-mini-2.0 is a compact multilingual instruction model tuned for speed, cost efficiency, and dep… Text · Open weights 5.8k HF downloads
  14. 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
  15. 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
  16. 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
  17. 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
  18. 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
  19. Kanana Nano Naver Kanana Nano 2.1B is the smallest model in Kakao’s Kanana family—built on 2.1 billion parameters. It… Text · Closed 3.8k HF downloads
  20. 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
  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. 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
  25. 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
  26. 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
  27. 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
  28. 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
  29. OUI-1 Thesys OUI-1 is a 26B parameter (4B active) diffusion based language model finetuned to generate user inte… Coding · Open weights 2.2k HF downloads
  30. Falcon-H1R 7B Technology Innovation Institute Falcon-H1R 7B is TII’s 7B reasoning-focused LLM, built on Falcon H1-7B with a hybrid Transformer pl… Text · Open weights 2.1k HF downloads
  31. Command A Reasoning Caldera Labs Command A Reasoning is Cohere’s first dedicated reasoning model: 111B parameters, 256K context, 32K… Text · Open weights 1.9k HF downloads
  32. Instella MoE 16B A3B SFT AMD Instella-MoE-16B-A3B-SFT is the supervised fine-tuning checkpoint of AMD's Instella-MoE model, a fu… Text · Open weights 1.9k HF downloads
  33. Llama 3.1 Nemotron Ultra NVIDIA Llama 3.1 Nemotron Ultra is an NVIDIA-optimized deployment of Meta’s Llama 3.1, packaged for high-t… Text · Open weights 1.7k HF downloads
  34. LongCat 2.0 Meituan LongCat-2.0 is an open-source MoE language model with 1.6 trillion total parameters (~48B activated… Text · Open weights 1.6k HF downloads
  35. Qwen 2.5 Coder 32B Alibaba Code-focused Qwen model family aimed at code generation, reasoning, and fixing across multiple para… Coding · Open weights 1.6k HF downloads
  36. DBRX Instruct Databricks DBRX Instruct is Databricks’ chat-tuned Mixture-of-Experts model (≈132B total, subset active per to… Text · Open weights 1.5k HF downloads