Nvidia’s DGX Spark Personal AI Supercomputer Launches 15 October

TL;DR:

  • Nvidia’s DGX Spark delivers petaflop AI performance in a desktop form factor
  • Priced at $3,999 (approximately £3,100), available from 15 October
  • Handles AI models with up to 200 billion parameters
  • Multiple manufacturers releasing customised versions

Nvidia has announced that its DGX Spark “personal AI supercomputer” will go on sale on 15 October 2025, bringing data centre-class AI capabilities to desktop computing. The machine, originally unveiled as “Digits” earlier this year, represents a significant shift in making sophisticated AI model development accessible to individual researchers and developers.

Context and Background

The DGX Spark features Nvidia’s GB10 Grace Blackwell Superchip with 128GB of unified memory and up to 4TB of NVMe SSD storage. Despite its compact desktop form factor, the system delivers one petaflop of AI performance—capable of one million billion calculations per second—and can handle AI models containing up to 200 billion parameters whilst running from a standard power outlet.

The system will be available directly from nvidia.com and through select partners in the United States at a launch price of $3,999, representing a £1,000 increase from the $3,000 price point announced earlier this year. Major manufacturers including Acer, Asus, Dell, Gigabyte, HP, Lenovo, and MSI are releasing customised versions, with the Acer Veriton GN100 confirmed at the same $3,999 price point.

Looking Forward

Nvidia CEO Jensen Huang has positioned the launch as a democratising force in AI development, stating that “placing an AI supercomputer on the desks of every data scientist, AI researcher and student empowers them to engage and shape the age of AI.” This move addresses a longstanding barrier where sophisticated AI experimentation required expensive data centre access or cloud computing resources.

The company has also developed a larger “Station” variant, though no release timeline has been announced for this higher-capacity system. The availability of desktop AI supercomputers at this price point could accelerate independent AI research and development, particularly in academic and small research team settings.

Source Attribution:

Share this article