Skip to content
AIMarketCap

SmolVLA

Model
Hugging FacePart of LeRobotactive

Compact 450-million-parameter vision-language-action model for affordable real-world robotics.

Released
Jun 3, 2025
Context window
—
Modality
textimagerobot actions
Open source
Yes
API available
—
Releases
1

Releases

1
Jun 3, 2025SmolVLA releasedSmolVLA

Hugging Face released SmolVLA, a 450M vision-language-action model trained for affordable, open robotic manipulation.

Hugging Face Model releaseHugging FaceSmolVLA