---
title: Fara1.5-9B Computer Use Agent
emoji: 🖱️
colorFrom: green
colorTo: gray
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
short_description: Visual grounding demo for Fara1.5-9B computer use agent
python_version: "3.12"
startup_duration_timeout: 30m
---

# Fara1.5-9B Computer Use Agent — Visual Grounding Demo

This Space demonstrates [Fara1.5-9B](https://huggingface.co/microsoft/Fara1.5-9B),
a 9B multimodal **computer use agent** by Microsoft Research AI Frontiers.

## How it works

1. Upload a screenshot of a web page
2. Describe the task the agent should perform (e.g. "Click the search box and type 'wireless headphones'")
3. Fara1.5-9B analyzes the screenshot and predicts the next grounded action
4. The predicted action (click coordinate, text to type, scroll, etc.) is visualized on the image with a marker

## Technical details

- **Model**: microsoft/Fara1.5-9B (9B parameters, bf16, ~18GB VRAM)
- **Base**: Qwen3.5-9B, fine-tuned with FaraGen1.5 synthetic data
- **Coordinate system**: Normalized 0–1000 per axis, mapped onto a 1440×900 viewport
- **Output format**: Chain-of-thought reasoning followed by an XML-tagged `computer_use` tool call
- **System prompt**: The verbatim system prompt from the model card

The model predicts pixel-level click coordinates in a normalized 0–1000 space,
which are rescaled to the actual screenshot dimensions for visualization.