LLM EXPLORER 56,604 MODELS INDEXED

UI TARS 7B DPO by ByteDance-Seed

By ByteDance-Seed · 2043 downloads

UI TARS 7B DPO is an open-source language model by ByteDance-Seed. Features: 7b LLM, VRAM: 16.6GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.2.

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

UI TARS 7B DPO Parameters and Internals

LLM NameUI TARS 7B DPO
Repository πŸ€—https://huggingface.co/ByteDance-Seed/UI-TARS-7B-DPO 
Model Size7b
Required VRAM16.6 GB
Updated2026-08-08
MaintainerByteDance-Seed
Model Typeqwen2_vl
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2VLForConditionalGeneration
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to UI TARS 7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 VL 7B Instruct32K / 16.7 GB3337
UI TARS 7B SFT32K / 33.2 GB1077180
ZeroGUI AndroidLab 7B32K / 16.6 GB315
ZeroGUI OSWorld 7B32K / 16.6 GB287
Qwen2 VL 7B Instruct Bf1632K / 16.6 GB504
Qwen2 VL 7B Bf1632K / 16.6 GB221
UI TARS 7B DPO 8bit32K / 9.4 GB371
OlmOCR 7B 0225 Preview 4bit32K / 5.6 GB221
...L 7B Instruct Abliterated 8bit32K / 8.9 GB291
Qwen2 VL 7B Instruct 4bit32K / 4.7 GB6482
Note: green Score (e.g. "73.2") means that the model is better than ByteDance-Seed/UI-TARS-7B-DPO.