OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
4.1M Pulls 5 Tags Updated 1 month 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.
69.9M Pulls 35 Tags Updated 4 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.
12.8M Pulls 58 Tags Updated 4 weeks ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
136.8K Pulls 8 Tags Updated 1 month ago
Magistral is a small, efficient reasoning model with 24B parameters.
644.3K Pulls 5 Tags Updated 4 months ago
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
5,221 Pulls 3 Tags Updated 1 week ago