Project Digits will be almost Top 500-fast and is powered by Nvidia's band's new GB10 Grace Blackwell Superchip. With the Nvidia AI software stack preinstalled and 128GB of memory, developers can prototype, fine-tune, and infer large AI models of up to 200B parameters locally and then seamlessly deploy to the data center or cloud.

The key to its performance is the GB10 Grace Blackwell Superchip, designed in partnership with MediaTek. It also boasts 128GB of RAM and up to a 4TB NVMe SSD. Running Nvidia’s Linux-based DGX OS, it will be capable of running 200-billion-parameter large language models or 405-billion-parameter models if pairing two Digits together.

One of the biggest announcements in Nvidia CEO Jensen Huang’s CES keynote was the small “Project Digits” AI supercomputer, and if you want to get an idea of just how tiny the $3,000 machine is in real life,

Tech giant NVIDIA announced Project DIGITS, the world’s smallest AI supercomputer, on Monday, January 6. It’s a personal device that allows AI researchers, data scientists, and students to harness the power of the NVIDIA Grace Blackwell platform.

Nvidia founder and CEO Jensen Huang had an extensive CES 2025 address, detailing everything from Nvidia’s next set of GPUs, its plans for embracing the next era of robotics and automotive innovation,

The blueprints were announced at both Consumer Electronics Show, where CEO Jensen Huang delivered a keynote and discussed blueprints among many other announcements, and in a blog post by Justin Boitano,