Advancing the Coding Capability
96.7K Pulls 1 Tag Updated 4 months ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
90.2K Pulls 1 Tag Updated 4 months ago
Exceptional multilingual capabilities to elevate code engineering
43.5K Pulls 1 Tag Updated 4 months ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
59.7K Pulls 1 Tag Updated 5 months ago
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
46K Pulls 1 Tag Updated 5 months ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
9.3M Pulls 5 Tags Updated 6 months ago
The most powerful vision-language model in the Qwen model family to date.
3.6M Pulls 59 Tags Updated 6 months ago
Alibaba's performant long context models for agentic and coding tasks.
5.1M Pulls 10 Tags Updated 7 months ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
664.6K Pulls 8 Tags Updated 7 months ago
MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.
105.2K Pulls 1 Tag Updated 6 months ago
Advanced agentic, reasoning and coding capabilities.
109.5K Pulls 1 Tag Updated 6 months 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.
62.6K Pulls 1 Tag Updated 7 months ago
The current, most capable model that runs on a single GPU.
36.2M Pulls 29 Tags Updated 4 months ago