Tencent has released UI-Mate-27B, an open-weight foundation model designed for long-horizon computer use across applications and operating systems. The 27-billion parameter model observes live screenshots to reason over visible states and produces structured keyboard and mouse actions for native desktop interaction.

  • Built on the Qwen3.6-27B base model with supervised fine-tuning and online reinforcement learning.
  • Supports general computer use from natural-language instructions and demonstration-guided workflows.
  • Features live-screen grounding rather than coordinate replay, allowing re-planning when interface states change.
  • Outputs structured actions compatible with pyautogui and provides an openAI-compatible serving interface.

The model is available under the Apache-2.0 license on Hugging Face and GitHub.