---
title: MobiZen-GUI-4B
canonical_url: "https://www.modelscope.cn/models/GUIAgent/MobiZen-GUI-4B"
md_url: "https://www.modelscope.cn/models/GUIAgent/MobiZen-GUI-4B.md"
repository: GUIAgent/MobiZen-GUI-4B
chinese_name: MobiZen-GUI-4B
last_updated: 2026-03-18
license: "Apache License 2.0"
model_type:
  - qwen3_vl
architectures:
  - Qwen3VLForConditionalGeneration
base_model_relation: finetune
parameters: 4.8B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - PyTorch
language:
  - zh
  - en
downloads: 51
stars: 1
---

# MobiZen-GUI-4B

> MobiZen-GUI-4B - GUIAgent 在 ModelScope 开源的模型。🌐 Project | 💻 Demo | 📄 Chinese Trajectory Data

GUIAgent/MobiZen-GUI-4B 是 ModelScope 魔搭社区上的 4.8B 参数机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: GUIAgent/MobiZen-GUI-4B
- **License**: Apache License 2.0
- **Parameters**: 4.8B
- **Downloads**: 51
- **Stars**: 1
- **Last updated**: 2026-03-18

Source: https://www.modelscope.cn/models/GUIAgent/MobiZen-GUI-4B

---

# <p align="center"><b>MobiZen-GUI-4B</b></p>

<p align="center">
🌐 <a href="https://github.com/alibaba/MobiZen-GUI">Project</a>  |
💻 <a href="https://github.com/alibaba/MobiZen-GUI/tree/main/demo">Demo</a>  |
📄 <a href="https://modelscope.cn/datasets/GUIAgent/CMGUI">Chinese Trajectory Data</a>
</p>

<p align="center">
  <a href="https://modelscope.cn/models/GUIAgent/MobiZen-GUI-4B/file/view/master/README.md?status=1">English</a> |
  <a href="https://modelscope.cn/models/GUIAgent/MobiZen-GUI-4B/file/view/master/README_CN.md?status=1">简体中文</a>
</p>

## Introduction

MobiZen-GUI-4B is a native GUI agent model built on Qwen3-VL. It is trained on a large, hand-curated corpus of Chinese mobile GUI interactions, the model has learned from hundreds of thousands of real Chinese app sessions spanning e-commerce, transport, social, and finance. Each record includes screenshots, touch traces, and Chinese instructions, giving the agent deep insight into Chinese UI conventions and workflows.

The goal of MobiZen-GUI-4B is to make it easier—and faster—to build and ship Chinese Mobile GUI agents. It delivers:

  - A 4-billion-parameter agent that runs completely on your own desktop or laptop.
  - Fast execution speed, relying only on a single image and historical actions. It relies solely on a single current image and historical actions, requiring no additional information, resulting in fast execution speed.
  - A turnkey inference kit that auto-handles ADB links and pulls in every required library.

What it can do
  
  - Runs on everyday machines: engineered for snappy response while keeping data on-device.
  - Sees and acts: spots buttons, text fields, lists, etc., then taps, types, swipes, or waits as needed.
  - Masters long procedures: carries out multi-stage jobs in food, ride-hailing, shopping, social, and other apps.
  - Works out of the box: copes with brand-new apps and shifting layouts without any extra fine-tuning or domain-specific tweaks.

## Usage

Please refer to [here](https://github.com/alibaba/MobiZen-GUI) to use MobiZen-GUI-4B.

## Deploy

We recommand deploy MobiZen-GUI-4B through vllm==0.11.0 / transformers==4.57.0.