What are the hardware requirements for UI TARS 1.5 7B 6bit?

UI TARS 1.5 7B 6bit requires approximately 6.9 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed UI TARS 1.5 7B 6bit and how large is it?

UI TARS 1.5 7B 6bit is developed by mlx-community, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate UI TARS 1.5 7B 6bit?

UI TARS 1.5 7B 6bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

UI TARS 1.5 7B 6bit by mlx-community — VRAM 6.9GB, 125K context

Name: UI TARS 1.5 7B 6bit
Author: mlx-community

UI TARS 1.5 7B 6bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 6.9GB, Context: 125K, License: apache-2.0, Quantized.

6bit Conversational En Endpoints compatible Gui Image-text-to-text Mlx Multimodal Quantized Qwen2 5 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/UI-TARS-1.5-7B-6bit

UI TARS 1.5 7B 6bit Parameters and Internals

LLM Name	UI TARS 1.5 7B 6bit
Repository 🤗	https://huggingface.co/mlx-community/UI-TARS-1.5-7B-6bit
Model Size	7b
Required VRAM	6.9 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen2_5_vl
Model Files	5.3 GB: 1-of-2 1.6 GB: 2-of-2
Supported Languages	en
Quantization Type	6bit
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	4.52.0.dev0
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Errors	replace

Rank the UI TARS 1.5 7B 6bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to UI TARS 1.5 7B 6bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 VL 7B Instruct 3bit	125K / 4.7 GB	56	1
Jedi 7B 1080p 4bit	125K / 4.9 GB	19	1
UI TARS 1.5 7B 4bit	125K / 4.9 GB	161	2
OlmOCR 2 7B 1025 Mlx 4bit	125K / 5.6 GB	126	1
Qwen2.5 VL 7B Instruct 4bit	125K / 5.6 GB	3486	4
Jedi 7B 1080p 6bit	125K / 6.9 GB	19	1
Qwen2.5 VL 7B Instruct 6bit	125K / 6.9 GB	107	3
Qwen2.5 VL 7B Instruct 8bit	125K / 8.9 GB	1759	17
OlmOCR 2 7B 1025 Mlx 8bit	125K / 9.4 GB	172	2
OlmOCR 7B 0725 8bit	125K / 9.4 GB	97	5