OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
4.9M 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.
73.3M Pulls 35 Tags Updated 5 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.
14.3M Pulls 58 Tags Updated 1 month ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
178.5K Pulls 8 Tags Updated 2 months ago
Magistral is a small, efficient reasoning model with 24B parameters.
760.9K Pulls 5 Tags Updated 5 months ago
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
21.4K Pulls 3 Tags Updated 1 month ago