OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
3.5M Pulls 5 Tags Updated 1 week 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.
66.6M Pulls 35 Tags Updated 3 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.
10.3M Pulls 58 Tags Updated 1 week ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
105.3K Pulls 8 Tags Updated 3 weeks ago
Magistral is a small, efficient reasoning model with 24B parameters.
520.3K Pulls 5 Tags Updated 4 months ago