OpenCUA / Qwen-CUA
Fully open desktop agents: weights, data and training code. They work on Windows, macOS and Linux; the latest Qwen-CUA controls a computer with ordinary clicks and keystrokes.
- Developer
- XLANG Lab (University of Hong Kong), China
- First release
- Jul 2025
- Latest release
- Aug 2026
- Sizes
- 7B – about 400B (MoE)
- License
- Commercial use allowedMIT (OpenCUA), Apache 2.0 (Qwen-CUA)
- Russian
- Not supported
- Running
- On your own serverNeeds a GPU
- Industries
- Documents and accounting, Software development
What it does
- Working in desktop software without an API
- Moving data between systems
- Running user scenarios for tests
Where it is used
Hardware requirements
Versions
- Qwen-CUA
- OpenCUA-72B
- OpenCUA-7B / 32B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can OpenCUA / Qwen-CUA be used in a commercial project?
Yes. License: MIT (OpenCUA), Apache 2.0 (Qwen-CUA). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does OpenCUA / Qwen-CUA need?
At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does OpenCUA / Qwen-CUA support Russian?
No. The model card lists its languages and Russian is not among them.
Where can I download OpenCUA / Qwen-CUA and what does it cost?
The OpenCUA / Qwen-CUA weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
A model that looks at a screenshot and controls the mouse and keyboard itself: clicks, fills in fields, navigates menus. The first generation and 1.5-7B are open; UI-TARS-2 weights were not released.
DetailsComputer-use agentsHoloH Company · FranceCommercial use with conditionsA French model family for controlling a browser and computer: precisely finds the right element on screen and handles multi-step tasks. The latest Holo3 and 3.1 are open under Apache 2.0.
DetailsComputer-use agentsEvoCUAMeituan · ChinaCommercial use allowedMeituan's computer-control agent, trained on a large number of simulated tasks in desktop software. It outputs clicks and keyboard input.
DetailsSource: huggingface.co/api/models?author=xlangai. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


