What are the hardware requirements for UI TARS 7B SFT?

UI TARS 7B SFT requires approximately 33.2 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 SFT and how large is it?

UI TARS 7B SFT is developed by ByteDance-Seed, 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 SFT?

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

UI TARS 7B SFT by ByteDance-Seed — VRAM 33.2GB, 32K context

Name: UI TARS 7B SFT
Author: ByteDance-Seed

UI TARS 7B SFT is an open-source language model by ByteDance-Seed. Features: 7b LLM, VRAM: 33.2GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.19.

Arxiv:2501.12326 Conversational En Endpoints compatible Eval-results Gui Image-text-to-text Multimodal Qwen2 vl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ByteDance-Seed/UI-TARS-7B-SFT

UI TARS 7B SFT Parameters and Internals

LLM Name	UI TARS 7B SFT
Repository 🤗	https://huggingface.co/ByteDance-Seed/UI-TARS-7B-SFT
Model Size	7b
Required VRAM	33.2 GB
Updated	2026-08-08
Maintainer	ByteDance-Seed
Model Type	qwen2_vl
Model Files	5.0 GB: 1-of-7 5.0 GB: 2-of-7 4.9 GB: 3-of-7 5.0 GB: 4-of-7 5.0 GB: 5-of-7 4.9 GB: 6-of-7 3.4 GB: 7-of-7
Supported Languages	en
Model Architecture	Qwen2VLForConditionalGeneration
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the UI TARS 7B SFT 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 SFT

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2 VL 7B Instruct	32K / 16.7 GB	33	37
UI TARS 7B DPO	32K / 16.6 GB	2043	230
ZeroGUI AndroidLab 7B	32K / 16.6 GB	31	5
ZeroGUI OSWorld 7B	32K / 16.6 GB	28	7
Qwen2 VL 7B Instruct Bf16	32K / 16.6 GB	50	4
Qwen2 VL 7B Bf16	32K / 16.6 GB	22	1
UI TARS 7B DPO 8bit	32K / 9.4 GB	37	1
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 Instruct 4bit	32K / 4.7 GB	648	2

Note: green Score (e.g. "73.2") means that the model is better than ByteDance-Seed/UI-TARS-7B-SFT.