RynnBrain1.1-2B

RynnBrain 1.1

<p align="center"> <img src="https://github.com/alibaba-damo-academy/RynnBrain/blob/main/cookbooks/assets/images/logo.png?raw=ture" style="width: 60%; height: auto;"> </p> <p align="center"><i>Towards More Capable and Generalizable Embodied Foundation Models</i></p> <p align="center"> 💫 <a href="https://alibaba-damo-academy.github.io/RynnBrain/"><b>Project Page</b></a> &nbsp;&nbsp;|&nbsp;&nbsp; 🤗 <a href="https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain-11"><b>Hugging Face</b></a> &nbsp;&nbsp;|&nbsp;&nbsp; 🤖 <a href="https://modelscope.cn/collections/DAMO_Academy/RynnBrain-11"><b>ModelScope</b></a> &nbsp;&nbsp;|&nbsp;&nbsp; 📚 <a href="https://github.com/alibaba-damo-academy/RynnBrain/tree/main/cookbooks"><b>Cookbooks</b></a> &nbsp;&nbsp;|&nbsp;&nbsp; 📄 <a href="https://arxiv.org/abs/2602.14979"><b>arXiv</b></a> </p>

News

• [2026.07.16] ✨✨ Release RynnBrain 1.1 checkpoints (2B / 9B / 122B-A10B) on <a href="https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain-11">Hugging Face</a> & <a href="https://modelscope.cn/collections/DAMO_Academy/RynnBrain-11">ModelScope</a>!
• [2026.07.16] ✨✨ Release the RynnBrain 1.1 Technical Report on <a href="https://arxiv.org/abs/2602.14979v1">arXiv</a>!

Introduction

We present RynnBrain 1.1, a systematic upgrade of RynnBrain for embodied intelligence. RynnBrain 1.1 is released in three scales: 2B, 9B, and 122B-A10B, extending the model family from compact dense models to its first 122B-level sparse-MoE model.

What's New in 1.1 🚀

• Unified Embodied Scaling to 122B: Establishes the first embodied brain model at the 122B scale under a unified training recipe shared across 2B, 9B, and 122B-A10B, enabling a systematic study of how embodied cognition, spatial reasoning, grounding, and planning evolve with scale.
• Real-robot VLA transfer: Bridges perception and action through RynnBrain-VLA, translating embodied understanding into real-robot control and demonstrating strong cross-platform generalization on Unitree G1, Astribot, and Tianji-Wuji across humanoid, bimanual, and dexterous-hand tasks.
• Native 3D and contact point grounding: Introduces explicit 3D-grounded training and a new contact point prediction task, extending RynnBrain from image-plane localization to metric 3D understanding and action-relevant interaction grounding.

Performance

• General Embodied Understanding

<p align="center"><i>RynnBrain 1.1-2B vs. other 2B-scale models</i></p> <p align="center"> <img src="https://github.com/alibaba-damo-academy/RynnBrain/blob/main/cookbooks/assets/images/RynnBrain1.1-2B.png?raw=ture" style="width: 80%; height: auto;"> </p>

• Real-Robot VLA Evaluation

<p align="center"><i>Real-robot VLA success rates vs. baselines</i></p> <p align="center"> <img src="https://github.com/alibaba-damo-academy/RynnBrain/blob/main/cookbooks/assets/images/VLA_results.png?raw=ture" style="width: 80%; height: auto;"> </p>

• 3D Grounding

<p align="center"><i>3D grounding accuracy vs. baselines</i></p> <p align="center"> <img src="https://github.com/alibaba-damo-academy/RynnBrain/blob/main/cookbooks/assets/images/3D_chart.png?raw=ture" style="width: 80%; height: auto;"> </p>

Model Zoo

Quick Start

Inference with 🤗 transformers

Minimal dependencies

pip install transformers==5.2.0

Run text generation

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "cookbooks/assets/object_location/images/000000086408.jpg"},
            {
                "type": "text",
                "text": "What appliance can be used to heat food quickly.\nGenerate coordinates for one object bounding box. Constraints: x1,y1,x2,y2 in [0,1000]. Response must be in the format: <object> (x1, y1), (x2, y2) </object>",
            },
        ],
    }
]

model_path = "Alibaba-DAMO-Academy/RynnBrain1.1-2B"
processor = AutoProcessor.from_pretrained(model_path)

model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    dtype=torch.bfloat16,
)
model.to("cuda")

model_inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    enable_thinking=False,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
)
model_inputs = model_inputs.to("cuda")

output_ids = model.generate(
    **model_inputs,
    max_new_tokens=256,
    do_sample=False,
)
output_ids = output_ids[:, model_inputs["input_ids"].size(1) :]
response = processor.decode(output_ids[0], skip_special_tokens=True)
print(response)

Inference with SGLang

For installation and advanced usages, please refer to the official documentation.

OpenAI-Compatible Serving

# launch server
python3 -m sglang.launch_server --model-path Alibaba-DAMO-Academy/RynnBrain1.1-2B --host 0.0.0.0 --port 8000

# inference using openai api
import base64
import io

from openai import OpenAI
from PIL import Image

def pil_to_url(image: Image.Image):
    image_format = image.format if image.format else 'PNG'
    buffered = io.BytesIO()
    image.save(buffered, format=image_format)
    img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
    return f'data:image/{image_format.lower()};base64,{img_str}'

messages = [
    {
        'role': 'user',
        'content': [
            {'type': 'image_url', 'image_url': {'url': pil_to_url(Image.open('cookbooks/assets/object_location/images/000000086408.jpg'))}},
            {'type': 'text', 'text': 'What appliance can be used to heat food quickly.\nGenerate coordinates for one object bounding box. Constraints: x1,y1,x2,y2 ∈ [0,1000]. Response must be in the format: <object> (x1, y1), (x2, y2) </object>'},
        ],
    }
]

client = OpenAI(api_key="", base_url="http://localhost:8000/v1")
response = client.chat.completions.create(
    model="default",
    messages=messages,
    stream=False,
).choices[0].message.content
print(response)

Offline Engine

import sglang as sgl
from transformers import AutoProcessor

def main():
    conversation = [
        {
            'role': 'user',
            'content': [
                {'type': 'image'},
                {'type': 'text', 'text': 'What appliance can be used to heat food quickly.\nGenerate coordinates for one object bounding box. Constraints: x1,y1,x2,y2 ∈ [0,1000]. Response must be in the format: <object> (x1, y1), (x2, y2) </object>'},
            ],
        }
    ]

    model_path = 'Alibaba-DAMO-Academy/RynnBrain1.1-2B'
    llm = sgl.Engine(model_path=model_path)
    processor = AutoProcessor.from_pretrained(model_path)

    prompt = processor.apply_chat_template(
        conversation,
        add_generation_prompt=True,
        tokenize=False,
    )

    output = llm.generate(
        prompt=prompt,
        image_data='cookbooks/assets/object_location/images/000000086408.jpg',
        sampling_params={"temperature": 0.8, "top_p": 0.95},
    )
    print(f"Prompt: {prompt}\nGenerated text: {output['text']}")

if __name__ == '__main__':
    main()

Cookbooks

Check out the cookbooks that showcase RynnBrain's capabilities in cognition, localization, reasoning, and planning.

Training

Pretraining & Evaluation

Please refer to RynnScale for details of pretraining and evaluation.

📑 Citation

If you find RynnBrain useful for your research and applications, please cite using this BibTeX:

@article{damo2026rynnbrain,
  title={RynnBrain: Open Embodied Foundation Models},
  author={Ronghao Dang, Jiayan Guo, Bohan Hou, Sicong Leng, Kehan Li, Xin Li, Jiangpin Liu, Yunxuan Mao, Zhikai Wang, Yuqian Yuan, Minghao Zhu, Xiao Lin, Yang Bai, Qian Jiang, Yaxi Zhao, Minghua Zeng, Junlong Gao, Yuming Jiang, Jun Cen, Siteng Huang, Liuyi Wang, Wenqiao Zhang, Chengju Liu, Jianfei Yang, Shijian Lu, Deli Zhao},
  journal={arXiv preprint arXiv:2602.14979v1},
  year={2026},
  url = {https://arxiv.org/abs/2602.14979v1}
}

@article{damo2026rynnbrain11,
  title={RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model},
  author={Kehan Li, Bohan Hou, Minghao Zhu, Tianyi Zhang, Zesen Cheng, Zhikai Wang, Sicong Leng, Xin Li, Xiao Lin, Biying Yao, Minghua Zeng, Jiangpin Liu, Ronghao Dang, Jiayan Guo, Siteng Huang, Haoyu Zhao, Heng Ping, Yaxi Zhao, Kexiang Wang, Tong Lu, Shengke Xue, Jiahao Tang, Yulei Wang, Zejing Wang, Jianwei Gao, Shijian Lu, Chengju Liu, Jianfei Yang, Mingxiu Chen, Deli Zhao},
  journal={arXiv preprint arXiv:2607.17977},
  year={2026},
  url = {https://arxiv.org/abs/2607.17977}
}