CES—NVIDIA today introduced NVIDIA^® Project DIGITS, a personal AI supercomputer that provides AI researchers, data scientists and students worldwide access to the power of the NVIDIA Grace Blackwell platform.

Project DIGITS features the new NVIDIA GB10 Grace Blackwell superchip, which provides a petaflop of AI computing power for prototyping, fine-tuning and operating large AI models.

Project DIGITS allows users to develop and run inferences on models using their own desktop system, and then seamlessly deploy the models to an accelerated cloud or data center infrastructure.

“AI will become mainstream in every application and in every industry. “Project DIGITS brings the Grace Blackwell superchip to millions of developers,” said Jensen Huang, founder and CEO of NVIDIA. “Putting an AI supercomputer on the desk of every data scientist, AI researcher and student will enable them to get involved and help shape the age of AI.”

The GB10 superchip delivers one petaflop of energy-efficient AI performance
The GB10 Superchip is a system-on-a-chip (SoC) based on the NVIDIA Grace Blackwell architecture, delivering up to 1 petaflop of AI performance at FP4 precision.

GB10 features an NVIDIA Blackwell GPU with latest generation CUDA® cores and fifth generation Tensor cores, connected via NVLink^®-C2C chip-to-chip connection to a powerful NVIDIA Grace™ CPU that contains 20 energy-efficient cores based on Arm architecture. MediaTek, a leader in Arm-based SoC designs, collaborated on the design of the GB10, contributing to its best-in-class power efficiency, performance and connectivity.

The GB10 superchip allows Project DIGITS to deliver powerful performance using only a standard electrical outlet. Each Project DIGITS features 128GB of unified, coherent storage and up to 4TB of NVMe storage. The supercomputer allows developers to run large language models with up to 200 billion parameters to drive AI innovation. Additionally with NVIDIA ConnectX^® Networking allows two Project DIGITS AI supercomputers to be connected to run models with up to 405 billion parameters.

Grace Blackwell AI supercomputing within reach
The Grace Blackwell architecture allows companies and researchers to prototype, refine and test models on on-premises Project DIGITS systems running Linux-based NVIDIA DGX OS, then seamlessly deploy them to NVIDIA DGX Cloud™, accelerated cloud instances or data center infrastructure.

This allows developers to build AI prototypes on Project DIGITS and then scale them on cloud or data center infrastructure, using the same Grace Blackwell architecture and NVIDIA AI Enterprise software platform.

Project DIGITS users can access an extensive library of NVIDIA AI software for experimentation and prototyping, including software development kits, orchestration tools, frameworks, and models available in the NVIDIA NGC Catalog and NVIDIA Developer Portal. Developers can refine models with the NVIDIA NeMo™ framework, accelerate data science with NVIDIA RAPIDS™ libraries, and run popular frameworks such as PyTorch, Python, and Jupyter notebooks.

To build agent AI applications, users can also leverage NVIDIA Blueprints and NVIDIA NIM™ microservices available through the NVIDIA Developer Program for research, development and testing. When AI applications are ready to move from experimental to production environments, the NVIDIA AI Enterprise license provides enterprise-grade security, support, and product releases of NVIDIA AI software.

Availability
Project DIGITS will be available in May from NVIDIA and top partners starting at $3,000. Sign up for alerts today.