MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
46.6K Pulls 1 Tag Updated 2 weeks ago
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
173.9K Pulls 7 Tags Updated 3 weeks ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
4.5M Pulls 58 Tags Updated 23 hours ago
A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks.
153.1K Pulls 1 Tag Updated 1 month ago
MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.
152K Pulls 1 Tag Updated 1 month ago
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
990.4K Pulls 4 Tags Updated 1 month 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.
211.8K Pulls 1 Tag Updated 2 months ago
Advancing the Coding Capability
81.2K Pulls 1 Tag Updated 3 months ago
Exceptional multilingual capabilities to elevate code engineering
34.5K Pulls 1 Tag Updated 3 months ago
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
115.2K Pulls 2 Tags Updated 3 months ago
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
333.8K Pulls 9 Tags Updated 2 weeks ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
731.3K Pulls 6 Tags Updated 3 months 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.
415.2K Pulls 6 Tags Updated 3 months ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
66.6K Pulls 1 Tag Updated 3 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
169.9K Pulls 6 Tags Updated 3 months ago
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
473.5K Pulls 10 Tags Updated 3 months ago
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
37.1K Pulls 1 Tag Updated 4 months ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
824.9K Pulls 16 Tags Updated 3 months ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
145.9K Pulls 6 Tags Updated 4 months ago
Kimi K2 Thinking, Moonshot AI's best open-source thinking model.
48.7K Pulls 1 Tag Updated 4 months ago