Nvidia’s AI Supercomputer for Personal Use: Project Digits
Introduction
If you were looking for your own personal AI supercomputer, Nvidia has you covered. The chipmaker announced at CES it’s launching a personal AI supercomputer called Project Digits in May. The heart of Project Digits is the new GB10 Grace Blackwell Superchip, which packs enough processing power to run sophisticated AI models while being compact enough to fit on a desk and run from a standard power outlet.
What is Project Digits?
Project Digits looks like a mini PC, and it’s designed for data scientists, AI researchers, and students. Each system comes equipped with 128GB of unified, coherent memory and up to 4TB of NVMe storage. For even more demanding applications, two Project Digits systems can be linked together to handle models with up to 405 billion parameters.
Key Features
- GB10 chip delivers up to 1 petaflop of AI performance (1 quadrillion AI calculations per second) at FP4 precision
- Features Nvidia’s latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink-C2C to a Grace CPU containing 20 power-efficient Arm-based cores
- Developed in collaboration with MediaTek to optimize power efficiency and performance
- Users get access to Nvidia’s AI software library, including development kits, orchestration tools, and pre-trained models available through the Nvidia NGC catalog
- Runs on Linux-based Nvidia DGX OS and supports popular frameworks like PyTorch, Python, and Jupyter notebooks
How Does it Work?
Users can develop and test their AI models locally on Project Digits, then deploy them to cloud services or data center infrastructure using the same Grace Blackwell architecture and Nvidia AI Enterprise software platform. The system is designed to be easy to use, with a user-friendly interface and a range of pre-trained models available for deployment.
Conclusion
Nvidia’s Project Digits is an exciting development in the world of AI, offering a powerful and accessible way for individuals to develop and deploy sophisticated AI models. With its compact design and affordable price tag, it’s likely to have a significant impact on the field of AI research and development.
Frequently Asked Questions
Q: What is the starting price of Project Digits?
A: $3,000
Q: What kind of processing power does Project Digits offer?
A: The GB10 chip delivers up to 1 petaflop of AI performance (1 quadrillion AI calculations per second) at FP4 precision.
Q: What kind of storage does Project Digits offer?
A: Each system comes equipped with up to 4TB of NVMe storage.
Q: What kind of AI software library is available with Project Digits?
A: Users get access to Nvidia’s AI software library, including development kits, orchestration tools, and pre-trained models available through the Nvidia NGC catalog.
Q: What kind of frameworks does Project Digits support?
A: The system runs on Linux-based Nvidia DGX OS and supports popular frameworks like PyTorch, Python, and Jupyter notebooks.

