NVIDIA's DGX Spark 'mini-supercomputer' will see its AIB models launch in the market by next month, following a strong response to the Founders Edition.
NVIDIA's DGX Spark Manages to Deliver 1,000 TOPS of AI Power, But Costs Around a Whopping $4,000
For those unaware, NVIDIA does have a product that does contribute to the 'AI PC' narrative, but it is more of a professional-oriented device, called the DGX Spark. It's the company's first foray into developing compact and capable computing devices, and now, according to a report by Ctee, it is claimed that custom models of the DGX Spark are set to launch in October, following uncertainity around whether the mini-supercomputer will gain widespread presence in the retail segment.
We have covered the AIB models of DGX Spark in depth, but for those unaware, SKUs from Acer, ASUS, Gigabyte, and MSI will be available. We had already showcased exclusive looks of some of these SKUs during our visit to Computex 2025. Delving a bit into the specifications of NVIDIA's DGX Spark, we are examining the features of the GB10 Grace Blackwell Superchip, which comes equipped with the powerful NVIDIA Blackwell GPU, featuring fifth-generation Tensor Cores and FP4 support, and delivering up to 1,000 trillion operations per second of AI compute.
Taiwanese AIB partners are expected to account for 70% of the DGX Spark production figures, indicating that consumers will widely adopt models from these manufacturers, as they will have a larger retail presence. Another interesting aspect of the GB10 Grace Blackwell Superchip is that it will likely reveal what NVIDIA's AI PC chips would look like, which are expected to be a combination of x86 architecture and NVIDIA's RTX GPU chiplets, following the partnership between Team Green and Intel.
The broader availability of DGX Spark systems is expected to occur in either Q4 or Q1 2026, and this would likely be the timeline when both AIB and FE models will be in stock across common retail partners.
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
