DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
35.1K Pulls 1 Tag Updated 6 days ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a 1M-token context window and three reasoning modes.
25.2K Pulls 1 Tag Updated 4 days ago
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
66.9K Pulls 1 Tag Updated 1 week ago
GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
123.1K Pulls 1 Tag Updated 3 weeks ago
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
6.3M Pulls 29 Tags Updated 2 weeks ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
7.7M Pulls 58 Tags Updated 4 weeks ago
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
1.1M Pulls 4 Tags Updated 2 months ago
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
1M Pulls 16 Tags Updated 4 months ago
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
808K Pulls 6 Tags Updated 4 months 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.
257.1K Pulls 7 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.
531.6K Pulls 10 Tags Updated 4 months 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.
265.7K Pulls 1 Tag 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.
452.3K Pulls 6 Tags Updated 4 months ago
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
415.5K Pulls 9 Tags Updated 1 month ago
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
103.2K Pulls 1 Tag Updated 1 month 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.
198.2K Pulls 1 Tag Updated 2 months ago
MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.
169K 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.
206.8K Pulls 6 Tags Updated 4 months ago
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
145.1K Pulls 2 Tags Updated 4 months ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
177.2K Pulls 6 Tags Updated 5 months ago