OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
1.8M Pulls 3 Tags Updated 3 weeks ago
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
60.1M Pulls 35 Tags Updated 2 months ago
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
7.3M Pulls 56 Tags Updated 3 weeks ago
Magistral is a small, efficient reasoning model with 24B parameters.
329.4K Pulls 5 Tags Updated 2 months ago
DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.
20.4K Pulls 4 Tags Updated yesterday