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.
48.3K Pulls 1 Tag Updated 6 days ago
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.
17.8K Pulls 1 Tag Updated 2 days ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
535.2K Pulls 22 Tags Updated 4 days 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.
114.7K Pulls 1 Tag Updated 2 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.
5.6M Pulls 29 Tags Updated 1 week ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
7.2M Pulls 58 Tags Updated 3 weeks ago
LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.
1.1M Pulls 6 Tags Updated 2 months 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
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
1.2M Pulls 4 Tags Updated 3 months ago
LFM2.5 is a new family of hybrid models designed for on-device deployment.
1.1M Pulls 5 Tags Updated 3 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.
793K 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.
245.2K Pulls 7 Tags Updated 1 month ago
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
282.9K Pulls 3 Tags Updated 2 months ago
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
105.5K Pulls 3 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.
528.4K 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.
260.6K Pulls 1 Tag Updated 2 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.
450.2K Pulls 6 Tags Updated 4 months ago
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
97K Pulls 1 Tag Updated 1 month ago
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
408.8K Pulls 9 Tags Updated 1 month ago