DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
48M Pulls 35 Tags Updated 1 week 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.
2.3M Pulls 35 Tags Updated 2 weeks ago
Magistral is a small, efficient reasoning model with 24B parameters.
5,462 Pulls 5 Tags Updated 3 days ago