Nvidia Unveils Two Personal AI Supercomputers

Nvidia made a splash at GTC 2025 by introducing a fresh range of "AI personal supercomputers," all powered by their innovative Grace Blackwell chip platform. During his keynote on Tuesday, Jensen Huang, Nvidia's founder and CEO, showcased two new powerhouses: DGX Spark (formerly known as Project Digits) and DGX Station. These machines are designed to help users prototype, fine-tune, and run AI models of various sizes right at the edge.
Huang proudly declared, "This is the computer of the age of AI. This is what computers should look like, and this is what computers will run in the future. And we have a whole lineup for enterprise now, from little, tiny ones to workstation ones." The DGX Spark, boasting Nvidia's GB10 Grace Blackwell Superchip, cranks out up to 1,000 trillion operations per second in AI computing. Meanwhile, the DGX Station comes equipped with the GB300 Grace Blackwell Ultra Desktop Superchip and a whopping 784GB of memory.
You can get your hands on the DGX Spark right now, but you'll have to wait a bit longer for the DGX Station, which is set to hit the market later this year through partners like Asus, Boxx, Dell, HP, and Lenovo.
Huang went on to say, "AI agents will be everywhere. How they run, what enterprises run, and how we run it will be fundamentally different. And so we need a new line of computers. And this is it."
For more details on all the exciting news and announcements from GTC, be sure to check out TechCrunch's live blog.
Related article
Nvidia's OpenClaw variant may solve its biggest challenge: security
Nvidia CEO Jensen Huang believes every company needs an OpenClaw strategy — and Nvidia is ready to supply it.During his GTC keynote on Monday, Huang announced that Nvidia has built NemoClaw, an enterprise-grade platform derived from the viral, local
Pentagon signs deals with Nvidia, Microsoft, AWS to deploy AI on classified networks
After previously reaching agreements with Google, SpaceX, and OpenAI, the U.S. Defense Department announced Friday that it has now signed deals with Nvidia, Microsoft, Amazon Web Services, and Reflection AI to deploy their AI technologies and models
Nvidia GTC Unveils NemoClaw, Robot Olaf, and $1 Trillion Bet
Loading the player…CEO Jensen Huang took the stage at Nvidia's GTC conference this week in his signature leather jacket to deliver a two-and-a-half-hour keynote, projecting $1 trillion in AI chip sales through 2027, declaring that every company needs
Related Special Topic Recommendations
Comments (43)
0/500
Dois supercomputadores pessoais de IA da Nvidia? Achei que iam anúnciar apenas um upgrade do GB200! kkk Isso prova que o Jensen está mesmo querendo dominar tudo. É impressionante como eles conseguem empacotar tanto poder num equipamento pessoal. Mas fico me perguntando: quem vai ter coragem e dinheiro para comprar uma dessas? Vai ser só para grandes laboratórios de novo? 🤔
Just when you think Nvidia's dominance can't get any crazier, they drop 'personal AI supercomputers'. The power for a single user is mind-blowing, but I can't help but wonder about the cost and the environmental footprint of these monsters. Feels like the arms race has officially reached your home office. 💻🔥
Na, da wird man ja neugierig! Diese neuen AI-Supercomputer von Nvidia könnten echt die Spielregeln ändern, oder? Spannend, wie die Technologie immer zugänglicher wird. Hoffentlich bleibt die ethische Diskussion da nicht hinterher. 🤖
¡Los nuevos supercomputadores de IA de Nvidia suenan increíbles! El chip Grace Blackwell parece un cambio de juego. No puedo esperar para tener uno, pero ¡espero que no sean demasiado caros! 🚀
Nvidia's new AI supercomputers are mind-blowing! The Grace Blackwell chip is a game-changer. DGX Spark sounds like a beast, but I'm curious about its real-world performance. Can't wait to see how it stacks up against other systems. Anyone got one to test? 🤓

Nvidia's OpenClaw variant may solve its biggest challenge: security
Nvidia CEO Jensen Huang believes every company needs an OpenClaw strategy — and Nvidia is ready to supply it.During his GTC keynote on Monday, Huang announced that Nvidia has built NemoClaw, an enterprise-grade platform derived from the viral, local
Pentagon signs deals with Nvidia, Microsoft, AWS to deploy AI on classified networks
After previously reaching agreements with Google, SpaceX, and OpenAI, the U.S. Defense Department announced Friday that it has now signed deals with Nvidia, Microsoft, Amazon Web Services, and Reflection AI to deploy their AI technologies and models
Nvidia GTC Unveils NemoClaw, Robot Olaf, and $1 Trillion Bet
Loading the player…CEO Jensen Huang took the stage at Nvidia's GTC conference this week in his signature leather jacket to deliver a two-and-a-half-hour keynote, projecting $1 trillion in AI chip sales through 2027, declaring that every company needs
Dois supercomputadores pessoais de IA da Nvidia? Achei que iam anúnciar apenas um upgrade do GB200! kkk Isso prova que o Jensen está mesmo querendo dominar tudo. É impressionante como eles conseguem empacotar tanto poder num equipamento pessoal. Mas fico me perguntando: quem vai ter coragem e dinheiro para comprar uma dessas? Vai ser só para grandes laboratórios de novo? 🤔
Just when you think Nvidia's dominance can't get any crazier, they drop 'personal AI supercomputers'. The power for a single user is mind-blowing, but I can't help but wonder about the cost and the environmental footprint of these monsters. Feels like the arms race has officially reached your home office. 💻🔥
Na, da wird man ja neugierig! Diese neuen AI-Supercomputer von Nvidia könnten echt die Spielregeln ändern, oder? Spannend, wie die Technologie immer zugänglicher wird. Hoffentlich bleibt die ethische Diskussion da nicht hinterher. 🤖
¡Los nuevos supercomputadores de IA de Nvidia suenan increíbles! El chip Grace Blackwell parece un cambio de juego. No puedo esperar para tener uno, pero ¡espero que no sean demasiado caros! 🚀
Nvidia's new AI supercomputers are mind-blowing! The Grace Blackwell chip is a game-changer. DGX Spark sounds like a beast, but I'm curious about its real-world performance. Can't wait to see how it stacks up against other systems. Anyone got one to test? 🤓





Home






