Scientists have created a new mini PC that is almost as powerful as a supercomputer but can fit in your bag.
The new device, dubbed “Project Digits,” is designed for developers, researchers, students and data scientists who work with artificial intelligence (AI). Its uses include running AI models that would have previously required tapping into massive data centers via the cloud, Nvidia’s CEO Jensen Huang announced at CES 2025 in Las Vegas.
Although the product design has not yet been finalized, it will be small enough to fit on your desk or even in your bag.
The device is powered by an Nvidia GB10 Grace Blackwell Superchip, which houses separate, linked components on a single chip to reduce the time it takes to move data between them.
The superchip features an Nvidia Blackwell graphics card and an Nvidia Grace processor, packaged with 128 gigabytes of memory and 4 terabytes of SSD storage.
Altogether, the device is approximately 1,000 times more powerful than the average laptop.
A mini PC that’s 1000-times more powerful than your PC or laptop
“NVIDIA’s Project DIGITS enables researchers in robotics, computer vision and autonomous systems to experiment, fine-tune and scale solutions faster than ever — all while fitting on your desk,” said Raquel Urtasun, a professor of computer science at the University of Toronto and founder of Waabi, a self-driving car company, in a statement. Waabi uses Nvidia’s technology in its fleet of self-driving trucks. “I’m excited to see what breakthroughs Project DIGITS will enable.”
Supercomputing power is measured in floating point operations per second (FLOPS). The most powerful supercomputers in the world deliver a little over 1,000 petaFLOPS of power (1 quintillion FLOPS). This makes them 1 million times more powerful than laptops, according to IBM.
Project Digits, by contrast, can provide 1 petaFLOPS of power. It won’t match the very best supercomputers, but it’s way more powerful than most desktop PCs and laptops and can fit into a considerably smaller chassis.
Using this “desktop supercomputer,” researchers can run large language models — generative AI tools like ChatGPT — that use up to 200 billion parameters, while two Project DIGITS devices can be connected to achieve 405 billion parameters. For reference, GPT-3.5, which powered the first version of ChatGPT when it launched in November 2022, was approximately 175 billion parameters in size, with each parameter being a variable that controls how a model processes and generates text.
The device’s design has not been finalized yet. Nvidia representatives did not share an image of the prototype, but they said it was set to launch in May for approximately $3,000 — with people able to register their interest in buying one.
