RynnBrain-30B-A3B

ManuelZnnmc/RynnBrain-30B-A3B

RynnBrain-30B-A3B is a image-text-to-text model from ManuelZnnmc. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

<p align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/66974212a9e7257fc37798dc/8eIGdvaZEuZKTcsjIAXXK.png" width="350" style="margin-bottom: 0.2;"/ <p <h2 align="center"<a href="https://gith…

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Parameters

16.6B

62.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors62.1 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
License: apache-2.0
Model type: qwen3_vl_moe
Access: Public
Created: Feb 16, 2026
Updated: Feb 16, 2026
SHA: b49bd9f7

Try a prompt

Base models

Qwen3-VL-30B-A3B-Instruct

Model card

From the Hugging Face model README

<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/66974212a9e7257fc37798dc/8eIGdvaZEuZKTcsjIAXXK.png" width="350" style="margin-bottom: 0.2;"/> <p <h2 align="center"><a href="https://github.com/alibaba-damo-academy/RynnBrain">RynnBrain: Open Embodied Foundation Models</a></h3> <h5 align="center"> If you like our project, please give us a star ⭐ on <a href="https://github.com/alibaba-damo-academy/RynnBrain">Github</a> for the latest update. </h5>

📰 News

[2026.02.02] Release RynnBrain family weights and inference code.
[2026.02.02] Add cookbooks for cognition, localization, reasoning, and planning.

✨ Introduction

RynnBrain aims to serve as a physics-aware embodied brain: it observes egocentric scenes, grounds language to physical space and time, and supports downstream robotic systems with reliable localization and planning outputs.

Key Highlights

Comprehensive egocentric understanding
Strong spatial comprehension and egocentric cognition across embodied QA, counting, OCR, and fine-grained video understanding.
Diverse spatiotemporal localization
Locates objects, target areas, and predicts trajectories across long episodic context, enabling global spatial awareness.
Physical-space grounded reasoning (RynnBrain family)
The broader RynnBrain family includes “Thinking” variants that interleave textual reasoning with spatial grounding to anchor reasoning in reality.
Physics-aware precise planning (RynnBrain family)
Integrates localized affordances/areas/objects into planning outputs to provide downstream VLA models with precise instructions.

🌎 Model Zoo

Model	Base Model	Huggingface	Modelscope
RynnBrain-2B	Qwen3-VL-2B-Instruct	Link	Link
RynnBrain-8B	Qwen3-VL-8B-Instruct	Link	Link
RynnBrain-30B-A3B (This Checkpoint)	Qwen3-VL-30B-A3B-Instruct	Link	Link
RynnBrain‑CoP-8B	RynnBrain-8B	Link	Link
RynnBrain‑Plan-8B	RynnBrain-8B	Link	Link
RynnBrain‑Plan-30B-A3B	RynnBrain-30B-A3B	Link	Link
RynnBrain‑Nav-8B	RynnBrain-8B	Link	Link

🚀 Main Results

🤖 Quick Start

Minimal dependencies:

pip install transformers==4.57.1

Run text generation:

from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("")
...

Cookbooks

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

Category	Cookbook name	Description
Cognition	1_spatial_understanding.ipynb	Shows the ability of model for spaital understanding in the video scene.
Cognition	2_object_understanding.ipynb	Shows how the model understands object categories, attributes, and relations and counting ability.
Cognition	3_ocr.ipynb	Examples of optical character recognition and text understanding in videos.
Location	4_object_location.ipynb	Locates specific objects with bounding boxes in an image or video based on instructions.
Location	5_area_location.ipynb	Identifies and marks specified regions by points in an image or video.
Location	6_affordance_location.ipynb	Finds areas or objects with specific affordances in an image of video.
Location	7_trajectory_location.ipynb	Infers and annotates trajectories or motion paths in an image or video.
Location	8_grasp_pose.ipynb	Present the model's abiltiy to predict robotic grasp poses from images.

Task: Image-Text-to-Text
Library: transformers
Type: qwen3_vl_moe
License: apache-2.0
Languages: en, zh
Created: Feb 16, 2026
Updated: Feb 16, 2026