Skip to main content
Specialist modelOpen weights

Qwen-Drive-1.0-4B

Qwen

Released
September 3, 2026
Data date
October 3, 2026

Qwen-Drive-1.0-4B is an open vision-language model for autonomous driving. A Qwen3.5-4B VLM remains the shared core, while a BEV perception head adds 3D detection, semantic occupancy, and map segmentation. A Planning Expert generates future vehicle trajectories.

The Hugging Face release includes the VLM checkpoint plus separate planner-sft, planner-rl, and perception modules. The Apache-2.0 weights run locally. The model is specialized for driving scenes, perception, visual question answering, and motion planning rather than general chat tasks.

Specifications and access

SpecificationValue and source
Model ID
Qwen/Qwen-Drive-1.0-4BSource
Model class
Vision-language model for autonomous drivingSource
Parameters
4 billion in the shared VLMSource
Perception
3D detection, semantic occupancy, and BEV map segmentationSource
Planning
Planning experts for direct and reasoning-based trajectoriesSource
License
Apache-2.0Source