Promote Sign in Sign up

Catalogs

Models

761 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. 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
  2. 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
  3. 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
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  10. 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
  11. Lizzy 7B Flower Labs Lizzy 7B is an open-weight 7 billion parameter language model from Flower Labs, built in the UK and… Text · Open weights 368 HF downloads
  12. Bielik 11B v2.6 Instruct SpeakLeash Bielik-11B-v2.6-Instruct is a Polish-focused 11B instruction model from SpeakLeash, aimed at strong… Text · Open weights 366 HF downloads
  13. MiroThinker v1.5 MiroMindAI MiroThinker v1.5 is an open-source deep research agent that orchestrates tools and web search to pl… Text · Closed 272 HF downloads
  14. Maincoder-1B Maincode Maincoder-1B is Maincode’s 1B-parameter transformer coding model, optimized for Python code generat… Text · Closed 267 HF downloads
  15. Mixtral 8x22B Mistral AI Mixtral 8x22B is a sparse mixture-of-experts language model that routes tokens to a subset of exper… Text · Open weights 223 HF downloads
  16. Stockmark 2 100b instruct Stockmark Stockmark-2-100B-Instruct is a 100B Japanese-focused instruction model built from scratch, trained… Text · Open weights 223 HF downloads
  17. LongCat Flash Thinking Meituan Large reasoning model built on a 560B MoE backbone, activating about 18.6 to 31.3B parameters for a… Text · Open weights 216 HF downloads
  18. Motif 2 12.7B Reasoning Motif Technologies Motif 2 12.7B Reasoning is a 12.7 billion parameter reasoning focused language model from Motif Tec… Text · Open weights 208 HF downloads
  19. Motif 12.7B Motif Technologies Motif 12.7B is a medium-large language model tuned for balanced reasoning, writing, and coding with… Text · Open weights 196 HF downloads
  20. Claude Sonnet 4.6 Anthropic Anthropic’s Sonnet 4.6 model for scaled production and complex tasks across coding, agents, and pro… Text · Closed 194 HF downloads
  21. Schematron 8B Inference 8B long-context HTML-to-JSON extraction model specialized for converting messy web pages into schem… Text · Open weights 161 HF downloads
  22. Gemini 2.5 Flash-Lite Google DeepMind Gemini 2.5 Flash-Lite is Google’s most cost-efficient Gemini 2.5 multimodal model for high-frequenc… Text · Closed 149 HF downloads
  23. Sky T1 NovaSky Sky-T1 is NovaSky’s open reasoning model family, including a 32B preview model that matches o1-prev… Text · Open weights 142 HF downloads
  24. PokeeResearch 7B Pokee AI PokeeResearchOSS is Pokee AI’s open source 7B DeepResearch agent. It runs multi turn web search and… Text · Open weights 128 HF downloads
  25. DBRX Base Databricks DBRX Base is Databricks’ open-weight Mixture-of-Experts foundation model (≈132B total parameters) b… Text · Open weights 117 HF downloads
  26. MiroThinker-1.7 MiroMindAI MiroThinker-1.7 is MiroMind’s deep-research agent family tuned for long-chain tool-augmented tasks,… Text · Open weights 101 HF downloads
  27. Covenant 72B Covenant AI Covenant-72B is a permissionless collaboratively trained 72B-parameter language model trained from… Text · Open weights 80 HF downloads
  28. GPT-4o OpenAI GPT-4o is OpenAI’s real-time, multimodal “omni” model. It understands text, images, and audio, and… Text · Closed 79 HF downloads
  29. Vicuna LMSYS Org AI model by LMSYS Org Text · Closed 42 HF downloads
  30. Alpie Core 169Pi Alpie-Core is 169Pi’s first-generation 4-bit quantized reasoning model, built on the DeepSeek-32B f… Text · Open weights 33 HF downloads
  31. Command A Translate Caldera Labs Command A Translate is Cohere’s enterprise translation model. It delivers high-quality, domain-adap… Text · Open weights 29 HF downloads
  32. Locai l1 large Locai Labs Locai L1-Large is an open instruction-tuned model built on Qwen3-235B Instruct, trained with Locai’… Text · Open weights 26 HF downloads
  33. CodeGemma Google DeepMind CodeGemma is Google’s open-weight Gemma coding model family for code completion, code generation, i… Text · Closed 25 HF downloads
  34. Gemini Pro Google DeepMind Gemini Pro is the balanced general-use tier of Google’s original Gemini 1.0 family. Text · Closed 25 HF downloads
  35. 1 Bit Bonsai 1.7B PrismML 1-bit Bonsai 1.7B is PrismML’s smallest Bonsai model, built for extremely fast on-device inference.… Text · Open weights 16 HF downloads
  36. PanGu-Alpha Huawei AI model by Huawei Text · Closed 16 HF downloads