Nvidia CEO and founder, Jensen Huang, personally delivered the company's innovative DGX Spark AI supercomputer to two prominent figures in the tech world: Elon Musk and Sam Altman. Described as the world's smallest supercomputer, the DGX Spark represents a significant advancement in compact, high-performance computing.

The first delivery was made to Elon Musk, CEO of SpaceX and Tesla, at SpaceX’s Starbase facility in Texas. This notable event coincided with SpaceX's preparations for the 11th test flight of its Starship, renowned as the world’s most powerful launch vehicle. Huang light-heartedly commented on the stark contrast, stating, “Imagine delivering the smallest supercomputer next to the biggest rocket.” Nvidia underscored the importance of this moment in a blog post, highlighting how the company’s initial nine-year-old investment in AI with the NVIDIA DGX-1 has now expanded its reach beyond traditional data centers.

Soon after his visit to Musk, Huang extended the same gesture to OpenAI founder Sam Altman. Greg Brockman, co-founder of OpenAI, publicly acknowledged the delivery on X, expressing his appreciation: “Thanks Jensen for the hand delivery of DGX Spark. Best delivery service ever. Amazing to see so much compute (1 petaflop!) in such a tiny form factor.” Altman reshared Brockman's post, reflecting on the technological progress since OpenAI received the original DGX-1 nine years ago, when it was first launched by Nvidia. Altman remarked, “Things have come a long way since the delivery of the DGX-1 9 years ago; amazing to see.”

The DGX Spark is a groundbreaking new class of computer, engineered to deliver a petaflop of AI performance. It boasts 128GB of unified memory, all contained within a compact desktop form factor. According to Nvidia’s blog, this powerful system provides developers with the capability to run inference on AI models containing up to 200 billion parameters and to fine-tune models of up to 70 billion parameters locally. Furthermore, the DGX Spark enables developers to create sophisticated AI agents and execute advanced software stacks directly on the device, offering unprecedented local AI development capabilities.