UI-TARS-1.5-7B is a 7-billion-parameter multimodal model released by ByteDance-Seed. It is specialized for understanding user interfaces, processing screenshots and other visual inputs, and powering agentic workflows. The model is available on Hugging Face with weights for local inference or integration into custom AI agent systems.
UI TARS 1.5 7B is a Foundation models & chat project. It focuses on enabling AI agents to perceive, understand, and interact with graphical user interfaces. UI TARS 1.5 7B is an open-source project aimed at developers. The project is open source (Apache-2.0). UI TARS 1.5 7B is available on the web, the command line, and API, and it can be self-hosted.
Behind UI TARS 1.5 7B is ByteDance, and it first shipped in 2025. Development happens publicly on GitHub with 11.2k stars. Among its 4 catalogued features are UI Understanding, Vision Processing, and Agent Capabilities.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do