Qwen3-VL-8B-Thinking-Mobile-SFT
This is the Mobile SFT model from the UI-MOPD project — an 8B model supervised-fine-tuned on mobile GUI interaction data. This checkpoint is released as an auxiliary artifact to demonstrate the quality of the Uni-GUI SFT data on the 8B tier and to enable community work such as Model-Merge (TIES / DARE) with other 8B GUI agents.
Note: This model is not used in the UI-MOPD student training path. In the UI-MOPD pipeline, the 8B student is cold-started directly from the
Qwen3-VL-8B-Thinkingbase and trained via on-policy distillation from the 32B teachers.
Model Description
Qwen3-VL-8B-Thinking-Mobile-SFT is fine-tuned from Qwen3-VL-8B-Thinking on mobile interaction trajectories from the Uni-GUI dataset. It is trained independently on the same mobile data used by the 32B Mobile Teacher, but at the 8B scale.
Key Highlights
- Base Model: Qwen3-VL-8B-Thinking
- Training Data: Mobile subset of Uni-GUI (~160K interaction steps across ~11.5K trajectories)
- Training: Supervised fine-tuning (SFT) on mobile GUI interaction trajectories
- Role: Auxiliary artifact — demonstrates Uni-GUI data quality on the 8B tier and enables Model-Merge experiments. Not used in the UI-MOPD student training path.
Relationship to the UI-MOPD Pipeline
The actual UI-MOPD training pipeline is:
- Stage 1: Supervised fine-tuning of Qwen3-VL-32B-Thinking on platform-specific data to produce a Desktop Teacher (46.3% on OSWorld) and a Mobile Teacher (16.2% on MobileWorld).
- Stage 2: The 8B student is cold-started from
Qwen3-VL-8B-Thinkingbase (not from any SFT checkpoint) and trained via DAPO (reinforcement learning) with multi-teacher on-policy distillation using platform-conditioned routing from the 32B teachers.
This 8B SFT model sits outside the distillation pipeline. It is trained independently on the same Uni-GUI mobile subset and released separately for the community.
Intended Use
This model is designed to:
- Be used as a standalone mobile GUI agent for executing mobile tasks (e.g., app navigation, settings control, messaging)
- Serve as a reference for evaluating the quality of the Uni-GUI SFT data on the 8B scale
- Provide a base for Model-Merge / TIES / DARE experiments with other 8B GUI agents
- Offer a baseline for comparing SFT-only vs. distillation-enhanced performance
How to Use
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
model = Qwen3VLForConditionalGeneration.from_pretrained(
"UI-MOPD/Qwen3-VL-8B-Thinking-Mobile-SFT",
torch_dtype="auto",
device_map="auto",
)
processor = AutoProcessor.from_pretrained("UI-MOPD/Qwen3-VL-8B-Thinking-Mobile-SFT")
Citation
@misc{lian2026uimopdmultiplatformonpolicydistillation,
title={UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning},
author={Niu Lian and Alan Chen and Zhehao Yu and Chengzhen Duan and Fazhan Liu and Hui Liu and Pei Fu and Jian Luan and Yaowei Wang and Shu-Tao Xia and Jinpeng Wang},
year={2026},
eprint={2607.04425},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2607.04425},
}
Related Resources
- Project Page: https://elisspectre.github.io/UI-MOPD/
- Code: https://github.com/EliSpectre/UI-MOPD
- Paper: UI-MOPD (arXiv)
- Desktop Teacher: UI-MOPD/Qwen3-VL-32B-Thinking-Desktop-Teacher
- Mobile Teacher: UI-MOPD/Qwen3-VL-32B-Thinking-Mobile-Teacher
- Student Model (cold-started from base, not from this SFT): UI-MOPD/Qwen3-VL-8B-Thinking-UI-MOPD-Student