Nvidia CEO Jensen Huang has confirmed that the upcoming DGX Spark systems are powered by the company’s N1 silicon, effectively revealing that the N1 and the previously announced GB10 Superchip are the same underlying processor. This clarification resolves long-standing speculation about the nature of the N1 SoC, which had been rumored to be a next-generation ARM-based chip for client devices. The GB10 Superchip, first introduced in connection with Project DIGITS at CES 2025, is already part of Nvidia’s DGX Spark lineup, designed for high-performance AI workloads in professional and desktop environments. It features a 20-core ARM-based CPU built using Nvidia’s Grace architecture and a powerful Blackwell-based GPU with 6,144 CUDA cores—matching the specs of the desktop RTX 5070. The chip is optimized for local AI inference and data processing, running on Nvidia’s Linux-based DGX OS rather than Windows. Huang made the confirmation during a recent webcast, stating, “We also have a new ARM product that's called N1. And that product is - that processor is going to go into the DGX Spark and many other versions of products like that. And so we're super excited about the ARM road map, and this doesn't affect any of that.” His mention of “many other versions” suggests the N1 could be a rebranded or slightly downgraded variant of the GB10, tailored for broader consumer or client use, while the full GB10 remains focused on professional and enterprise markets. This alignment between the GB10 and N1 reinforces Nvidia’s strategy to expand its in-house CPU capabilities beyond its Tegra legacy. The N1 marks the company’s most significant effort yet to bring its ARM-based architecture into mainstream computing, especially as the industry shifts toward specialized silicon for AI workloads. Despite the N1’s apparent existence in development, Nvidia has not announced a launch date. However, early testing of the N1 on Windows indicates progress toward a potential Windows-on-ARM release, though Huang did not confirm this. The GB10, in contrast, remains Linux-only and targeted at developers and AI professionals. The news comes alongside Nvidia’s newly announced collaboration with Intel, which includes joint development of x86-based and GPU products. Despite this partnership, Huang emphasized that the ARM and x86 roadmaps will continue independently, with no overlap or conflict between the two. This dual-track strategy allows Nvidia to maintain flexibility across different computing segments. In summary, the N1 SoC is not a separate chip but rather the same silicon as the GB10 Superchip, repurposed for broader client applications. While the exact timeline for the N1’s public release remains unclear, its integration into the DGX Spark and potential future devices signals Nvidia’s growing ambition in the ARM-based computing space.