Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
37.1K Pulls 4 Tags Updated 2 days ago
Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
46.1K Pulls 1 Tag Updated 1 week ago
The most powerful vision-language model in the Qwen model family to date.
1.4M Pulls 59 Tags Updated 3 months ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
389K Pulls 16 Tags Updated 1 month ago
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
309.8K Pulls 6 Tags Updated 1 month ago
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
312.2K Pulls 10 Tags Updated 2 months ago
Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models
154.5K Pulls 6 Tags Updated 1 month ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
135K Pulls 6 Tags Updated 1 month ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
344.6K Pulls 8 Tags Updated 4 months ago
Google's most intelligent model with SOTA reasoning and multimodal understanding, and powerful agentic and vibe coding capabilities.
99.7K Pulls 1 Tag Updated 2 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
69.5K Pulls 6 Tags Updated 1 month ago
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
53.9K Pulls 2 Tags Updated 1 month ago
Advancing the Coding Capability
39.5K Pulls 1 Tag Updated 1 month ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
60.8K Pulls 6 Tags Updated 2 months ago
Advanced agentic, reasoning and coding capabilities.
60.1K Pulls 1 Tag Updated 3 months ago
MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows.
51.6K Pulls 1 Tag Updated 3 months ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
27.3K Pulls 1 Tag Updated 1 month ago
Exceptional multilingual capabilities to elevate code engineering
15.9K Pulls 1 Tag Updated 1 month ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
27.4K Pulls 1 Tag Updated 3 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.
36.6K Pulls 1 Tag Updated 4 months ago