Date:

Nvidia Announces DGX Desktop “Personal AI Supercomputers”

Nvidia Unveils "Personal AI Supercomputers" for Developers and Researchers

Introducing DGX Spark and DGX Station

During Tuesday’s Nvidia GTX keynote, CEO Jensen Huang unveiled two "personal AI supercomputers" called DGX Spark and DGX Station, both powered by the Grace Blackwell platform. In a way, they are a new type of AI PC architecture specifically built for running neural networks, and five major PC manufacturers will build the supercomputers.

Design and Features

These desktop systems, first previewed as "Project DIGITS" in January, aim to bring AI capabilities to developers, researchers, and data scientists who need to prototype, fine-tune, and run large AI models locally. DGX systems can serve as standalone desktop AI labs or "bridge systems" that allow AI developers to move their models from desktops to DGX Cloud or any AI cloud infrastructure with few code changes.

Key Specifications

  • DGX Spark features the GB10 Grace Blackwell Superchip with Blackwell GPU and fifth-generation Tensor Cores, delivering up to 1,000 trillion operations per second for AI.
  • DGX Station includes the GB300 Grace Blackwell Ultra Desktop Superchip with 784GB of coherent memory and the ConnectX-8 SuperNIC supporting networking speeds up to 800Gb/s.

Manufacturing Partners

The DGX architecture serves as a prototype that other manufacturers can produce. Asus, Dell, HP, and Lenovo will develop and sell both DGX systems, with DGX Spark reservations opening today and DGX Station expected later in 2025. Additional manufacturing partners for the DGX Station include BOXX, Lambda, and Supermicro, with systems expected to be available later this year.

Pricing and Availability

Nvidia did not mention pricing for the units. However, in January, Nvidia mentioned that the base-level configuration for a DGX Spark-like computer would retail for around $3,000.

Conclusion

The DGX Spark and DGX Station are designed to revolutionize the way AI developers and researchers work, providing a new class of computers optimized for AI-native developers and applications. With the collaboration of five major PC manufacturers, these systems are expected to be widely available in the market.

Frequently Asked Questions

Q: What are DGX Spark and DGX Station?
A: DGX Spark and DGX Station are "personal AI supercomputers" designed for developers, researchers, and data scientists to prototype, fine-tune, and run large AI models locally.

Q: What are the key features of DGX Spark and DGX Station?
A: DGX Spark features the GB10 Grace Blackwell Superchip, while DGX Station includes the GB300 Grace Blackwell Ultra Desktop Superchip.

Q: Who will manufacture DGX Spark and DGX Station?
A: Asus, Dell, HP, and Lenovo will develop and sell both DGX systems, with additional partners including BOXX, Lambda, and Supermicro for DGX Station.

Q: What is the expected pricing for DGX Spark and DGX Station?
A: Nvidia did not mention pricing for the units, but a base-level configuration for a DGX Spark-like computer is expected to retail for around $3,000.

Latest stories

Read More

mimic Robotics unveils full-stack platform for dexterous robot manipulation

mimic Robotics has introduced a new robotic hand,...

Aetina expands Nvidia Jetson Thor portfolio with T3000 and T2000 support

Please switch off your ad blocker. Our website relies...

How to benchmark your system before running robotics simulations

Please switch off your ad blocker. Our website relies...

Has AI Agent Autonomy Redefined Robotics Safety and Control?

Robotics systems are learning to perceive, choose, and...

Opinion: Exotec managing director highlights key warehouse automation trends for 2026

Thomas Genestar, managing director of western Europe at...

MassRobotics opens RoboBoston 2026 sponsorships and announces AI career fair

MassRobotics has announced that it will host RoboBoston...

Agility Robotics opens new Fremont facility to accelerate physical AI development

Agility Robotics, a humanoid robotics and physical AI...

LEAVE A REPLY

Please enter your comment!
Please enter your name here