OPEN MODELS/VISION-LANGUAGE-ACTION/SMOLVLA
BEGINNERVISION-LANGUAGE-ACTIONNEW RELEASE

SmolVLA

Compact, efficient VLA built for consumer hardware

WHAT DOES THIS ACTUALLY DO?

This is the 'small but capable' version of the robot brain models. It runs on a normal gaming PC GPU — no data center required. Perfect for hobbyists, students, and anyone building their first robot.

PARAMETERS
450M
RELEASED
2024-11
LICENSE
Apache 2.0
ARCHITECTURE
Compact...
CAN I ACTUALLY RUN THIS?
9
Beginner Friendly
OUT OF 10

If you have a modern laptop or gaming PC, you can run this today. Hugging Face provides excellent documentation and the LeRobot library makes it plug-and-play.

DOWNLOAD WEIGHTS
Download from Hugging FaceView on GitHub
2GB disk space required
OVERVIEW

A 450M parameter Vision-Language-Action model from Hugging Face. Trained on the LeRobot dataset, designed for cost-effective deployment on consumer-grade GPUs.

TRAINED ON

LeRobot dataset (multi-task manipulation demonstrations)

ARCHITECTURE
Compact VLM + Action Head
CAPABILITIES
Low-latency inference
Consumer GPU deployment
Language-conditioned actions
Fine-tuning friendly
REAL ROBOTICS USE CASES
EDUCATIONAL

Teach a low-cost robot arm to sort objects

HOME ROBOTICS

Run on-device on a Raspberry Pi 5 setup

RESEARCH

Prototype new tasks without heavy compute

HARDWARE REQUIREMENTS
MIN VRAM
4GB
REC VRAM
8GB
MIN RAM
8GB
DISK SPACE
2GB
JETSON
Compatible
CPU ONLY
Supported
TESTED GPUs
RTX 3060RTX 4060M1/M2 MacAny 8GB GPU
DEPLOYMENT PATHS
Local PC
Runs on 4GB VRAM or CPUSUPPORTED
Docker
SUPPORTED
ROS2
Via LeRobot integrationSUPPORTED
Jetson Nano
CPU mode supportedSUPPORTED
Raspberry Pi
Slow but functionalSUPPORTED
Cloud
SUPPORTED
RELATED PAPERS
LeRobot: Making AI Accessible for Robotics
RELATED ORGANIZATIONS
Hugging FaceLeRobot
ORGANIZATIONS
Hugging Face
DIFFICULTY
BEGINNER

Anyone with a computer can run this

COMPUTE8/10
SETUP7/10
BEGINNER-FRIENDLY9/10
EDGE DEPLOYMENT
Jetson Compatible
CPU-only Supported
Community →

Seeded and planned prompts — not live forum activity yet.