Hugging Face says its new robotics model is so efficient it can run on a MacBook | TechCrunch

It’s becoming a little easier to build sophisticated robotics projects at home.

Earlier this week, AI dev platform Hugging Face released an open AI model for robotics called SmolVLA. Trained on “compatibly licensed,” community-shared datasets, SmolVLA outperforms much larger models for robotics in both virtual and real-world environments, Hugging Face claims.

“SmolVLA aims to democratize access to vision-language-action [VLA] models and accelerate research toward generalist robotic agents,” writes Hugging Face in a blog post. “SmolVLA is not only a lightweight yet capable model, but also a method for training and evaluating generalist robotics [technologies].”

SmolVLA is a part of Hugging Face’s rapidly expanding effort to establish an ecosystem of low-cost robotics hardware and software. Last year, the company launched LeRobot, a collection of robotics-focused models, datasets, and tools. More recently, Hugging Face acquired Pollen Robotics, a robotics startup based in France, and unveiled several inexpensive robotics systems, including humanoids, for purchase.

SmolVLA, which is 450 million parameters in size, was trained on data from LeRobot Community Datasets, specially marked robotics datasets shared on Hugging Face’s AI development platform. Parameters, sometimes referred to as “weights,” are the internal components of a model that guide its behavior.

Hugging Face claims that SmolVLA is small enough to run on a single consumer GPU — or even a MacBook — and can be tested and deployed on “affordable” hardware, including the company’s own robotics systems.

In an interesting twist, SmolVLA also supports an “asynchronous inference stack,” which Hugging Face says allows the model to separate the processing of a robot’s actions from the processing of what it sees and hears. As the company explains in its blog post, “[b]ecause of this separation, robots can respond more quickly in fast-changing environments.”

Techcrunch event Save now through June 4 for TechCrunch Sessions: AI Save $300 on your ticket to TC Sessions: AI—and get 50% off a second. Hear from leaders at OpenAI, Anthropic, Khosla Ventures, and more during a full day of expert insights, hands-on workshops, and high-impact networking. These low-rate deals disappear when the doors open on June 5. Exhibit at TechCrunch Sessions: AI Secure your spot at TC Sessions: AI and show 1,200+ decision-makers what you’ve built — without the big spend. Available through May 9 or while tables last. Berkeley, CA | REGISTER NOW

SmolVLA is available for download from Hugging Face. Already, a user on X claims to have used the model to control a third-party robotic arm:

🚀 SmolVLA — feels like a BERT moment for robotics 🤖

I tried it on the Koch Arm:

Inference on RTX 2050 (4GB), fine-tuned with just 31 demos, and matches/outperforms single-task baselines 🔥

Big thanks to @RemiCadene @danaubakirova @mustash97 @francesco__capu 🙌 pic.twitter.com/TiBkAZGwkM — Xingdong Zuo (@XingdongZ) June 4, 2025

It’s worth noting that Hugging Face is far from the only player in the nascent open robotics race.

Nvidia has a collection of tools for open robotics, and startup K-Scale Labs is building the components for what it’s calling “open-source humanoids.” Other formidable firms in the segment include Dyna Robotics, Jeff Bezos-backed Physical Intelligence, and RLWRLD.

Original Author: Kyle Wiggers | Source: TechCrunch