Computer-use agentsImage + text

UI-TARS

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.

Developer
ByteDance Seed, China
First release
Jan 2025
Latest release
Apr 2025
Sizes
2B – 72B
License
Commercial use allowedApache 2.0 (UI-TARS-2 weights were not released)
Russian
Not supported
Ready-made builds
GGUF, AWQ, GPTQ
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Working in legacy software without an API
  • Filling in forms and moving data between systems
  • UI autotests from plain-language scenarios

Where it is used

Back office and accountingIT and testingOperations teams

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. UI-TARS-1.5-7B
  2. UI-TARS 2B / 7B / 72B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can UI-TARS be used in a commercial project?

Yes. License: Apache 2.0 (UI-TARS-2 weights were not released). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does UI-TARS 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 UI-TARS support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download UI-TARS and what does it cost?

The UI-TARS 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

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Computer-use agentsOpenCUA / Qwen-CUAXLANG Lab (University of Hong Kong) · ChinaCommercial use allowed

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.

DetailsComputer-use agentsHoloH Company · FranceCommercial use with conditions

A 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 agentsGUI-Owl / Mobile-AgentAlibaba (Tongyi Lab, X-PLUG) · ChinaCommercial use allowed

Models for controlling phones and computers from the Mobile-Agent project: they work with Android, Windows, macOS and the browser; version 1.5 has a reasoning mode.

Details

Source: huggingface.co/api/models?author=ByteDance-Seed. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.