What are the hardware requirements for UI TARS 7B DPO 8bit?

UI TARS 7B DPO 8bit requires approximately 9.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed UI TARS 7B DPO 8bit and how large is it?

UI TARS 7B DPO 8bit 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 7B DPO 8bit?

UI TARS 7B DPO 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

UI TARS 7B DPO 8bit by mlx-community — VRAM 9.4GB, 32K context

Name: UI TARS 7B DPO 8bit
Author: mlx-community

UI TARS 7B DPO 8bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 9.4GB, Context: 32K, License: apache-2.0, Quantized.

8bit Conversational En Endpoints compatible Gui Image-text-to-text Mlx Multimodal Quantized Qwen2 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/UI-TARS-7B-DPO-8bit

UI TARS 7B DPO 8bit Parameters and Internals

LLM Name	UI TARS 7B DPO 8bit
Repository 🤗	https://huggingface.co/mlx-community/UI-TARS-7B-DPO-8bit
Model Size	7b
Required VRAM	9.4 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen2_vl
Model Files	5.3 GB: 1-of-2 4.1 GB: 2-of-2
Supported Languages	en
Quantization Type	8bit
Model Architecture	Qwen2VLForConditionalGeneration
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.49.0
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the UI TARS 7B DPO 8bit 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 7B DPO 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2 VL 7B 4bit	32K / 4.7 GB	32	3
Qwen2 VL 7B Instruct 4bit	32K / 4.7 GB	648	2
OlmOCR 7B 0225 Preview 4bit	32K / 5.6 GB	22	1
...L 7B Instruct Abliterated 8bit	32K / 8.9 GB	29	1
Qwen2 VL 7B 8bit	32K / 8.9 GB	19	1
Qwen2 VL 7B Instruct 8bit	32K / 8.9 GB	36	2
Qwen2 VL 7B Instruct	32K / 16.7 GB	33	37
Qwen2 VL 7B Instruct AWQ	32K / 6.9 GB	10752	22
Qwen2 VL 7B Instruct GPTQ Int4	32K / 7 GB	2588	14
Qwen2 VL 7B Instruct GPTQ Int8	32K / 10.2 GB	1266	31

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/UI-TARS-7B-DPO-8bit.