---

library_name: transformers

base_model:

• Alibaba-DAMO-Academy/RynnBrain1.1-2B

license: apache-2.0

language:

• en

pipeline_tag: image-text-to-text

tags:

• text-generation-inference
• robotics
• embodied-ai
• egocentric
• spatiotemporal
• vision-language-model
• video-understanding
• grounding
• planning
• navigation
• ocr
• image-text-to-text
• video-text-to-text
• custom_code

---

RynnBrain1.1-2B-GGUF

> RynnBrain1.1-2B is the smallest checkpoint in Alibaba DAMO Academy's RynnBrain 1.1 family of open embodied foundation models, built on Qwen3.5-2B and released alongside 9B and 122B-A10B (the family's first sparse-MoE model) variants under a unified training recipe designed to systematically study how embodied cognition, spatial reasoning, grounding, and planning evolve with scale. As part of this generation's upgrades, it introduces native 3D and contact-point grounding — extending beyond image-plane localization to metric 3D understanding via explicit 3D-grounded training and a new instruction-conditioned contact-point prediction task — and bridges perception to action through RynnBrain-VLA, translating embodied understanding into real-robot control with demonstrated cross-platform generalization on the Unitree G1, Astribot, and Tianji-Wuji platforms across humanoid, bimanual, and dexterous-hand tasks. The model handles spatial and object understanding, object/area/affordance/trajectory grounding, and both image and video inputs, outputting structured coordinate predictions (e.g., <object>(x1,y1),(x2,y2)</object> bounding boxes) for tasks like locating objects in a scene, and supports inference via Hugging Face transformers or SGLang (OpenAI-compatible serving or offline engine), with training and evaluation details documented separately in the companion RynnScale repository; it is released under Apache-2.0.

Model Files

File Name | Quant Type | File Size | File Link |

|-----------|------------|-----------|-----------|

| RynnBrain1.1-2B.BF16.gguf | BF16 | 3.78 GB | Download |

| RynnBrain1.1-2B.F16.gguf | F16 | 3.78 GB | Download |

| RynnBrain1.1-2B.F32.gguf | F32 | 7.54 GB | Download |

| RynnBrain1.1-2B.Q2_K.gguf | Q2_K | 969 MB | Download |

| RynnBrain1.1-2B.Q3_K_L.gguf | Q3_K_L | 1.16 GB | Download |

| RynnBrain1.1-2B.Q3_K_M.gguf | Q3_K_M | 1.1 GB | Download |

| RynnBrain1.1-2B.Q3_K_S.gguf | Q3_K_S | 1.02 GB | Download |

| RynnBrain1.1-2B.Q4_0.gguf | Q4_0 | 1.2 GB | Download |

| RynnBrain1.1-2B.Q4_K_M.gguf | Q4_K_M | 1.27 GB | Download |

| RynnBrain1.1-2B.Q4_K_S.gguf | Q4_K_S | 1.21 GB | Download |

| RynnBrain1.1-2B.Q5_0.gguf | Q5_0 | 1.37 GB | Download |

| RynnBrain1.1-2B.Q5_K_M.gguf | Q5_K_M | 1.41 GB | Download |

| RynnBrain1.1-2B.Q5_K_S.gguf | Q5_K_S | 1.37 GB | Download |

| RynnBrain1.1-2B.Q6_K.gguf | Q6_K | 1.56 GB | Download |

| RynnBrain1.1-2B.Q8_0.gguf | Q8_0 | 2.01 GB | Download |

| RynnBrain1.1-2B.mmproj-bf16.gguf | mmproj-bf16 | 671 MB | Download |

| RynnBrain1.1-2B.mmproj-f16.gguf | mmproj-f16 | 671 MB | Download |

| RynnBrain1.1-2B.mmproj-f32.gguf | mmproj-f32 | 1.33 GB | Download |

| RynnBrain1.1-2B.mmproj-q8_0.gguf | mmproj-q8_0 | 365 MB | Download |

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp