> ## Documentation Index
> Fetch the complete documentation index at: https://aegean.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# SmolVLA

> A compact, community-driven Vision-Language-Action model from Hugging Face, designed to run on a single consumer GPU and integrate with the LeRobot stack.

**SmolVLA** is Hugging Face's compact Vision-Language-Action model, built on top of the [LeRobot](https://github.com/huggingface/lerobot) library. It is designed to be small enough to fine-tune and deploy on a single consumer GPU, while remaining competitive with larger open VLAs on standard manipulation benchmarks.

## Pointers

* Paper: Shukor et al. (2025). [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://arxiv.org/abs/2506.01844)
* Code and weights: [`huggingface/lerobot`](https://github.com/huggingface/lerobot), the upstream library that hosts SmolVLA training, inference, and dataset utilities
* LeRobot documentation: [huggingface.co/docs/lerobot](https://huggingface.co/docs/lerobot)
* Model hub: [SmolVLA on Hugging Face](https://huggingface.co/lerobot)

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/aegean-ai/eaia/edit/main/src/book/vla-agents/smolvla/index.mdx) or [file an issue](https://github.com/aegean-ai/eaia/issues/new/choose).
</Callout>