GTA1-7B-4bit

mlx-community/GTA1-7B-4bit

GTA1-7B-4bit is a machine learning model from mlx-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

This model is covnert by mlxvlm from HelloKKMe/GTA1-7B.

Downloads · 30 days

24% of all-time downloads

All-time downloads

119

Public

Repo size

6.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors6.1 GB · 100%

At a glance

License: apache-2.0
Model type: qwen2_5_vl
Access: Public
Created: Sep 22, 2025
Updated: Sep 22, 2025
SHA: 059b27a6

Base models

HelloKKMe/GTA1-7B

Model card

From the Hugging Face model README

This model is covnert by mlx_vlm from HelloKKMe/GTA1-7B.

Model Description

GTA1-7B is a SOTA GUI grounding model, trained based on UI-TARS-1.5-7B for GUI agent tasks. It establishes state-of-the-art performance across diverse benchmarks, achieves 50.1%, 92.4%, and 67.7% accuracies on Screenspot-Pro, Screenspot-V2, and OSWorld-G benchmarks.

Model	Size	Open Source	ScreenSpot-V2	ScreenSpotPro	OSWORLD-G
OpenAI CUA	—	❌	87.9	23.4	—
Claude 3.7	—	❌	87.6	27.7	—
JEDI-7B	7B	✅	91.7	39.5	54.1
SE-GUI	7B	✅	90.3	47.0	—
UI-TARS	7B	✅	91.6	35.7	47.5
UI-TARS-1.5*	7B	✅	89.7*	42.0*	64.2*
UGround-v1-7B	7B	✅	—	31.1	36.4
Qwen2.5-VL-32B-Instruct	32B	✅	91.9*	48.0	59.6*
UGround-v1-72B	72B	✅	—	34.5	—
Qwen2.5-VL-72B-Instruct	72B	✅	94.00*	53.3	62.2*
UI-TARS	72B	✅	90.3	38.1	—
GTA1 (Ours)	7B	✅	92.4 <sub>(∆ +2.7)</sub>	50.1<sub>(∆ +8.1)</sub>	67.7 <sub>(∆ +3.5)</sub>
GTA1 (Ours)	32B	✅	93.2 <sub>(∆ +1.3)</sub>	53.6 <sub>(∆ +5.6)</sub>	61.9<sub>(∆ +2.3)</sub>
GTA1 (Ours)	72B	✅	94.8<sub>(∆ +0.8)</sub>	58.4 <sub>(∆ +5.1)</sub>	66.7<sub>(∆ +4.5)</sub>

Note:

The base models of GTA1-32B/72B are Qwen2.5-VL-32B/72-Instruct.

Quick Start

mlx_vlm.generate --model mlx-community/GTA1-7B-4bit \
  --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

Type: qwen2_5_vl
License: apache-2.0
Created: Sep 22, 2025
Updated: Sep 22, 2025