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. Carbon-8B Hugging Face Carbon-8B is an open-source 8B generative DNA foundation model for DNA/RNA sequence generation, sco… Text · Open weights 1.2k HF downloads
  2. Apertus v1.1 4B Instruct Swiss AI Initiative A 4B parameter instruction-tuned language model created via pre-training distillation from the Aper… Text · Open weights 1.2k HF downloads
  3. BLOOMZ BigScience BLOOMZ is an instruction-tuned, multilingual version of BLOOM. It follows natural language instruct… Text · Closed 1.2k HF downloads
  4. WebWorld 8B Alibaba WebWorld-8B is Qwen’s open web-agent model for autonomous browser interaction and online task compl… Text · Closed 1.1k HF downloads
  5. ZGCM 1 7B Zhongguancun Academy ZGCM-1-7B is ZGCAGI’s fully open 7.39B dense language model for mathematical reasoning, long-contex… Multimodal · Open weights 1.1k HF downloads
  6. Ling 2.6 1T AntGroup Ling-2.6-1T is inclusionAI’s trillion-parameter flagship instruct model for real-world agents. It i… Multimodal · Open weights 1k HF downloads
  7. nanowhale Hugging Face nanowhale is a miniature DeepSeek-V4-style language model project, built to reproduce the core Deep… Text · Open weights 918 HF downloads
  8. Ring 2.6 1T AntGroup Ring-2.6-1T is inclusionAI’s open-source 1T-parameter text-generation reasoning model for agent wor… Multimodal · Open weights 879 HF downloads
  9. Gemini 3.8 Flash Google DeepMind Gemini 3.8 Flash is a multimodal model in the Gemini 3 family, built for long horizon software engi… Multimodal · Closed 867 HF downloads
  10. Schematron 3B Inference 3B long-context HTML-to-JSON extraction model tuned for fast, cheap structured extraction on standa… Text · Open weights 814 HF downloads
  11. Breeze 7B Instruct MediaTek Breeze-7B-Instruct is MediaTek Research’s instruction-tuned 7B model built on top of Mistral-7B and… Text · Open weights 813 HF downloads
  12. Apertus v1.1 0.5B Instruct Swiss AI Initiative Apertus-v1.1-0.5B-Instruct is a 0.5B parameter multilingual instruction-tuned language model built… Text · Open weights 805 HF downloads
  13. Apertus v1.1 1.5B Instruct Swiss AI Initiative Apertus-v1.1-1.5B-Instruct is a 1.5B parameter instruction-tuned language model built on a dense tr… Text · Open weights 803 HF downloads
  14. Instella MoE 16B A3B Base AMD Instella-MoE-16B-A3B-Base is the long-context checkpoint AMD designates as the final base model in… Text · Open weights 799 HF downloads
  15. WizardCoder WizardLM AI model by WizardLM Text · Open weights 775 HF downloads
  16. Trinity Nano Arcee AI Trinity Nano Base is the base 6B (1B active) Trinity Nano checkpoint, pre–fine-tuning, meant to be… Text · Open weights 768 HF downloads
  17. Instella MoE 16B A3B Pretrain AMD Instella-MoE-16B-A3B-Pretrain is the base pre-training checkpoint of AMD's Instella-MoE model, a fu… Text · Open weights 740 HF downloads
  18. Antares 350M Cisco Systems Antares 350M is a compact security-focused language model from Cisco for locating vulnerable source… Coding · Open weights 705 HF downloads
  19. Motif 2.6B Motif Technologies Motif 2.6B is Motif Technologies' ultra lightweight 2.6 billion parameter language model, built to… Text · Open weights 657 HF downloads
  20. BTL-4 Bad Theory Labs BTL-4 is Bad Theory Labs’ open 35B agentic reasoning model for tool use, software engineering, long… Multimodal · Open weights 654 HF downloads
  21. Instella MoE 16B A3B DPO AMD Instella-MoE-16B-A3B-DPO is the direct preference optimization checkpoint of AMD's Instella-MoE mod… Text · Open weights 652 HF downloads
  22. Instella MoE 16B A3B Midtrain AMD Instella-MoE-16B-A3B-Midtrain is the mid-training checkpoint of AMD's Instella-MoE model, a fully o… Text · Open weights 638 HF downloads
  23. Marco-o1 Alibaba Marco-o1 is Alibaba International Digital Commerce’s open reasoning model line aimed at real-world… Text · Open weights 591 HF downloads
  24. Apertus v1.1 4B Swiss AI Initiative Apertus-v1.1-4B is a 4B parameter open-source base language model created via pre-training distilla… Text · Open weights 574 HF downloads
  25. Apertus v1.1 1.5B Swiss AI Initiative Apertus-v1.1-1.5B is a 1.5 billion parameter base language model trained via distillation from an 8… Text · Open weights 561 HF downloads
  26. NousCoder 14B Nous Research NousCoder-14B is a 14B-parameter coding model post-trained from Qwen3-14B with RL, tuned for compet… Text · Open weights 537 HF downloads
  27. Trinity Large Preview Arcee AI Trinity Large Preview is a 400B-parameter (about 13B active) frontier Trinity MoE model with long-c… Text · Open weights 536 HF downloads
  28. Nemotron Labs Audex 30B A3B NVIDIA Nemotron-Labs-Audex-30B-A3B is a unified audio-text large language model from NVIDIA built on a 30B… Multimodal · Open weights 512 HF downloads
  29. Macaron V1 Venti Macaron Macaron-V1-Venti is a 748 billion parameter agent model post-trained on GLM-5.2, combining a frozen… Text · Open weights 504 HF downloads
  30. Macaron V1 Coding Venti Macaron Macaron-V1-Coding-Venti is a coding-specialized build of Macaron-V1-Venti with the coding LoRA spec… Coding · Open weights 501 HF downloads
  31. Baichuan M3 235B Baichuan Intelligent Technology Baichuan-M3-235B is a medical-enhanced large language model trained to model clinical inquiry and d… Text · Open weights 499 HF downloads
  32. Macaron V1 Tall Macaron Macaron-V1-Tall is a 50 billion parameter agent model post-trained from Qwen 3.6, using the same Mi… Text · Open weights 473 HF downloads
  33. Hunyuan-Large Tencent Hunyuan-Large is Tencent’s flagship large language model in the Hunyuan family. It’s built for adva… Text · Open weights 468 HF downloads
  34. Ulam-1-Small Ulam.ai Ulam-1-Small is a 3.086B-parameter open-weight language model from Ulam AI, released under the MIT… Text · Open weights 417 HF downloads
  35. Kanana 1.5 Naver Kanana-1.5-v-3B is a 3B-parameter vision–language model in Kakao’s Kanana line. It can process both… Text · Closed 399 HF downloads
  36. ERNIE 4.5-300B-A47B Baidu ERNIE 4.5-300B-A47B is Baidu’s frontier Mixture-of-Experts ERNIE 4.5 variant—~300B total parameters… Text · Closed 369 HF downloads