OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
4.4M Pulls 5 Tags Updated 1 month ago
The most powerful vision-language model in the Qwen model family to date.
175.4K Pulls 59 Tags Updated 2 weeks ago
Alibaba's performant long context models for agentic and coding tasks.
676.4K Pulls 10 Tags Updated 1 month ago
Advanced agentic, reasoning and coding capabilities.
20.2K Pulls 1 Tag Updated 1 month ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
146.4K Pulls 8 Tags Updated 1 month ago
MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.
17.6K Pulls 1 Tag Updated 2 weeks ago
A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.
13.5K Pulls 1 Tag Updated 1 month ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
6,755 Pulls 1 Tag Updated 1 week ago