Mage-VL-Cowork
A compact 4B model that operates a computer by itself: it looks at a screenshot and clicks, and when that is more efficient it switches to the command line and edits files with code. Both roles are in one model, with no external orchestrator. On the OSWorld-Verified test (50 steps) it scores 66.0%, which the authors say is the best result among 4B models, and 87.5% on operating-system tasks. It was trained from the intermediate Mage-VL in five stages, with a set of almost 294 thousand synthetic tasks over 6,915 skills. The context for training and running is 32,768 tokens, and the architecture holds up to 262,144. It suits office automation and assistants on your own computer. The figures come from the authors.
- Developer
- Microsoft, USA
- First release
- Oct 2026
- Latest release
- Oct 2026
- Sizes
- 4B
- License
- Commercial use allowedApache 2.0
- Russian
- Not stated
- Running
- On your own serverNeeds a GPU
- Industries
- Software development, Customer support, Documents and accounting
What it does
- an agent that works in applications through screenshots and the command line
- automating office tasks on your own computer without a cloud
- a prototype assistant that operates the desktop
Where it is used
Hardware requirements
Versions
- Mage-VL-Cowork 4B
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 Mage-VL-Cowork be used in a commercial project?
Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Mage-VL-Cowork need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 Mage-VL-Cowork support Russian?
The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.
Where can I download Mage-VL-Cowork and what does it cost?
The Mage-VL-Cowork 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
One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.
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.
DetailsComputer-use agentsUI-VenusAnt Group (inclusionAI) · ChinaCommercial use with conditionsAn Ant Group family for finding elements on screen and completing tasks in phone and computer interfaces. UI-Venus-2 was specifically trained to refuse dangerous actions. In October LBS-27B came out (Apache 2.0, based on Qwen3.8-27B): it learns to pick and zoom into the needed parts of an image on interface markup, and carries this skill over to ordinary questions about pictures.
DetailsSource: huggingface.co/microsoft/Mage-VL-Cowork. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.