All setups
Set up this box
A notebook with Qwen3-VL on disk
A JupyterLab box holding the Qwen3-VL-4B vision-language weights, already downloaded.
Set up this boxWorkload
Notebooks
Preinstalled
JupyterLab + PyTorch preinstalled
Weights on disk
Qwen/Qwen3-VL-4B-Instruct
What you get
- JupyterLab and PyTorch installed and started for you on first boot.
- The Qwen3-VL-4B-Instruct weights downloaded into the box before you open it.
- A vision-language model takes images in and returns text. You supply the processor and generation code.
- Notebooks, pip installs and sample images stay on the disk between sessions.
The weights are downloaded onto the box before you open it. Nothing is running them for you. You bring your own code, or use whatever the box has installed. For what card this needs and what it costs an hour right now, see the GPU requirements for Qwen/Qwen3-VL-4B-Instruct.
Why this one is here
Its GPU-requirements page took 87 impressions at average position 10.6 over 28 days.
