Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen3-VL/llms.txt

Use this file to discover all available pages before exploring further.

Qwen3-VL provides a browser-based user interface that allows you to interact with the model through a web interface. This is useful for testing and demonstrating the model’s capabilities.

​
Prerequisites

Install the required dependencies: 
pip install -r requirements_web_demo.txt

​
Launch the Web Demo

Run the web demo using the following command: 
python web_demo_mm.py -c /your/path/to/qwen3vl/weight
After running the command, you’ll see a link generated in the terminal: 
Running on local: http://127.0.0.1:7860/
Open this link in your browser to interact with the model. You can try text, images, videos, or other multimodal features.

​
Docker-Based Web Demo

For a quick start, you can use the pre-built Docker image: 
cd docker && bash run_web_demo.sh -c /your/path/to/qwen3vl/weight --port 8881
This will launch the web interface on port 8881.

​
Features

  • Multi-Modal Input: Upload and process images, videos, and text
  • Interactive Interface: User-friendly web-based chat interface
  • Real-Time Responses: Get immediate feedback from the model
  • Easy Setup: Simple command-line launch

​
Docker Image

To simplify the deployment process, Qwen3-VL provides Docker images with pre-built environments: 
docker run --gpus all --ipc=host --network=host --rm --name qwen3vl \
  -it qwenllm/qwenvl:qwen3vl-cu128 bash

​
Docker Benefits

  • Pre-configured environment
  • GPU support included
  • Only requires driver installation and model files
  • Quick deployment without dependency management

​
Tips

  • Ensure you have sufficient GPU memory for the model size you’re using
  • The web interface supports multiple image formats and video files
  • You can adjust the port number if 7860 is already in use

Build docs developers (and LLMs) love

Get started for freeTalk to us