---
license: apache-2.0
base_model:
- ByteDance-Seed/UI-TARS-1.5-7B
---

This model is convert by mlx_vlm from [ByteDance-Seed/UI-TARS-1.5-7B](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B)

## Model Description

UI-TARS-1.5 is ByteDance's open-source multimodal agent built upon a powerful vision-language model. It is capable of effectively performing diverse tasks within virtual worlds.

The released UI-TARS-1.5-7B focuses primarily on enhancing general computer use capabilities and is not specifically optimized for game-based scenarios, where the UI-TARS-1.5 still holds a significant advantage.

| **Benchmark Type** | **Benchmark**                      | **UI-TARS-1.5-7B** | **UI-TARS-1.5** |
|--------------------|------------------------------------|--------------------|-----------------|
| Computer Use       | [OSWorld](https://arxiv.org/abs/2404.07972)              | 27.5               | **42.5**        |
| GUI Grounding      | [ScreenSpotPro](https://arxiv.org/pdf/2504.07981v1) | 49.6               | **61.6**        |

P.S. This is the performance of UI-TARS-1.5-7B and UI-TARS-1.5 on OSWorld and ScreenSpotProd.


## Quick Start
```shell
mlx_vlm.generate --model flin775/UI-Tars-1.5-7B-4bit-mlx \
  --max-tokens 1024 \
  --temperature 0.0 \
  --prompt "List all contacts’ names and their corresponding grounding boxes([x1, y1, x2, y2]) from the left sidebar of the IM chat interface, return the results in JSON format." \
  --image https://wechat.qpic.cn/uploads/2016/05/WeChat-Windows-2.11.jpg
```