Nvidia has announced its latest innovation, Project Digits, a personal AI supercomputer designed for developers, researchers, and students. Set to launch in May, Project Digits combines cutting-edge performance with desktop convenience, powered by Nvidia’s new GB10 Grace Blackwell Superchip. Starting at $3,000, the compact system offers unprecedented AI processing capabilities previously reserved for larger, energy-intensive setups.
Read: Meta announces huge policy shift towards free speech and simplified moderation
Project Digits supports AI models with up to 200 billion parameters and features a sleek design reminiscent of a Mac Mini. For demanding applications, two systems can be linked to handle models with up to 405 billion parameters—on par with Meta’s Llama 3.1 model.
“AI will be mainstream in every application for every industry,” said Nvidia CEO Jensen Huang. “With Project Digits, the Grace Blackwell Superchip comes to millions of developers, placing an AI supercomputer on the desks of every data scientist, AI researcher, and student.”
The system boasts 128GB of unified memory—far exceeding typical laptops—and up to 4TB of NVMe storage. The GB10 chip delivers 1 petaflop of AI performance at FP4 precision, leveraging Nvidia’s latest CUDA cores and Tensor Cores. It connects via NVLink-C2C to a Grace CPU featuring 20 power-efficient Arm-based cores, developed in collaboration with MediaTek for optimized performance and energy efficiency.
Project Digits runs on the Linux-based Nvidia DGX OS, supporting frameworks like PyTorch, Python, and Jupyter notebooks. Developers can fine-tune models using Nvidia’s NeMo framework and accelerate workflows with RAPIDS libraries. Additionally, users gain access to Nvidia’s AI software library, including pre-trained models and tools through the Nvidia NGC catalogue.
The system enables local development and testing of AI models, which can then be deployed to cloud services or data centres using the same Grace Blackwell architecture and Nvidia AI Enterprise software.
Nvidia has expanded its portfolio to include more accessible devices. In December, it introduced the Jetson Orin Nano Super—a $249 AI computer for hobbyists and startups capable of handling models with up to 8 billion parameters.
With Project Digits, Nvidia aims to democratize AI development, empowering individuals to shape the future of artificial intelligence.
