Brain
Hugging Face's compact 450M parameter VLA model for accessible robotics. Part of the LeRobot framework, designed for low-compute training and deployment on consumer hardware.
Foundation model · Maturity: Research · Open source
Machine-readable surfaces
- Markdown mirror: /brains/smolvla.md
- RSS feed: /brains/smolvla/feed.xml
- JSON-LD: embedded in this page’s head
- REST API: /v1/brains/501f1b47-683d-400e-afc8-74beff0d8937
- Revision history: /brains/smolvla/history
- Data documentation: /data
- Query this programmatically: Deploy MCP
Architecture
Compact VLA, 450M params
Developed by (1)
Common questions
What is SmolVLA?
Hugging Face's compact 450M parameter VLA model for accessible robotics. Part of the LeRobot framework, designed for low-compute training and deployment on consumer hardware.
Who developed SmolVLA?
SmolVLA is credited to Hugging Face on the DEPLOY registry. Each developer attribution is verified via primary sources.
Is SmolVLA open source?
Yes. SmolVLA is recorded as open-source / open-weights on the DEPLOY registry, meaning model weights or source code are publicly available.
What type of AI is SmolVLA?
SmolVLA is a foundation model, built on a Compact VLA, 450M params architecture on the DEPLOY registry.
What is SmolVLA's maturity stage?
SmolVLA is at the research stage on the DEPLOY maturity ladder. Research stage means active development without commercial deployments on file.
Which robots run on SmolVLA?
No robot models on the DEPLOY registry are recorded as running SmolVLA. DEPLOY wires brain-to-model connections only when the wiring is verifiable from primary sources; absence may reflect pre-deployment or unverified manufacturer claims.
Methodology: Unreviewed · no sources on file · last reviewed 2026-08-09
Verification posture
Unreviewed
Low confidence
Review state
Stable
Last reviewed 2026-08-09
Maturity + lifecycle
Maturity stage: research
The framework is documented at /methodology. Corrections at /corrections. Reviewer: DEPLOY editorial team.
Methodology surface for SmolVLA.Canonical ID 501f1b47-683d-400e-afc8-74beff0d8937