123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
230.2K Pulls 6 Tags Updated 5 months ago
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
560.9K Pulls 10 Tags Updated 5 months ago
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
59.8K Pulls 1 Tag Updated 6 months ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
1.2M Pulls 16 Tags Updated 5 months ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
194.6K Pulls 6 Tags Updated 6 months ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
2.1M Pulls 1 Tag Updated 6 months ago
MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.
2.2M Pulls 1 Tag Updated 7 months ago
Advanced agentic, reasoning and coding capabilities.
The most powerful vision-language model in the Qwen model family to date.
4M Pulls 59 Tags Updated 7 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.
75K Pulls 1 Tag Updated 8 months ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
692K Pulls 8 Tags Updated 8 months ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
10M Pulls 5 Tags Updated 7 months ago
Alibaba's performant long context models for agentic and coding tasks.
5.8M Pulls 10 Tags Updated 8 months ago
The current, most capable model that runs on a single GPU.
37.3M Pulls 29 Tags Updated 5 months ago