RynnUnify-Base

RynnUnify-Base is the SFT-stage unified multimodal model from the RynnUnify family, integrating a reasoning VLM with video world-model generation and action/plan generation capabilities.

• Architecture: Cosmos3OmniModel (plan generator + vision generation)
• VLM backbone: Qwen3-VL-8B-Instruct
• Precision: bfloat16, 7 safetensors shards (~31.5 GB)
• Loading requires the cosmos3 custom code module (trust_remote_code=True)

Part of the RynnUnify collection: RynnUnify-Base | RynnUnify-Agentic-Reasoner | RynnUnify-WAM-RoboCasa

Citation

@misc{rynnunify2026,
  title={RynnUnify: Towards Unified Embodied Brain},
  author={Minghao Zhu and Bohan Hou and Kun Xiang and Zixuan Wang and Yinzhou Tang and Yifei Yang and Zhikai Wang and Tianyi Zhang and Kehan Li and Haoyu Zhao and Siteng Huang and Leigang Qu and Sicong Leng and Dongchi Huang and Mingxiu Chen and Shijian Lu and Yue Wang and Xiaodan Liang and Zhenyu Zeng and Deli Zhao and Chengju Liu and Jianfei Yang and Xin Li},
  year={2026},
}