NVIDIA Enters Desktop AI Market with GB10 Grace Blackwell Chip, ASUS Leads Launch

Nvidia's first desktop PC chip lands this month -- Asus leads with Ascend GX10 Grace Blackwell desktop platform

Actual systems based on Nvidia's GB10 Grace Blackwell platform will be launched starting July 22, according to an Asus invitation, spotted by VideoCardz, promoting the event. The company plans to re-introduce its Ascend GX10 mini-PC on the day. However, the presentation itself barely indicates availability timeframe, or actual price, though both were touched upon by Nvidia itself previously. "Asus Ascent GX10 Product Launch: Discover the power of the compact Asus Ascent GX10," a statement in the flyer published by VideoCardz reads. "Learn about its key advantages and how it empowers Al development. Nvidia Keynote Speaker: Hear from an Nvidia expert on the cutting-edge features of DGX Spark Software Stack - and how they are redefining Al performance." The description clearly puts the Asus Ascend GX10 system beyond 'just mini PCs' and skyrockets the unit right into the workstation and edge AI space. Nvidia's GB10 Superchip system-in-package (SiP) integrates a Grace CPU that packs 10 high-performance Arm Cortex-X925 cores running up to 3.90 GHz with 10 power-efficient Cortex-A725 cores, alongside a Blackwell GPU capable of delivering 1 PetaFLOPS of FP4 compute throughput for AI workloads. The SiP features a 256-bit memory interface supporting 128GB of unified LPDDR5X memory, reaching bandwidths up to 273 GB/s, which is comparable to the memory subsystem of Apple's M4 Pro. Nvidia positions the GB10 platform as an AI solution that delivers data center-level performance in a compact form-factor suitable for workstations and edge deployments. The unit is expected to come at a steep price, though, something that Asus does not clear up at this point. Nvidia emphasizes the SiP's unified memory architecture, massive FP4 throughput, and strong single-thread performance as key advantages over traditional CPU-GPU setups. In this way, Nvidia presents GB10 as an ideal solution for building and running LLMs, generative AI applications, and other demanding workloads on desktop-class systems. However, leaked performance Geekbench figures of the GB10 may disappoint. When it comes to general-purpose compute in Geekbench, the GB10 is close to Qualcomm's Snapdragon X Elite and near Apple's M3 processor, based on the leaked scores. Given that this processor targets AI workstation use cases, high single-thread performance remains an important factor. Asus' Ascend GX10 mini-PC should closely resemble those of Nvidia's own DGX Spark small form-factor system that is priced at $3,000. In addition to Asus, Dell, HP, and Lenovo are prepping their own versions of the DGX Spark, though prices of such machines as well as their positioning remains unclear.

Nvidia GB10 Grace Blackwell Desktop Chip Ascend GX10 Asus Launch Details

Nvidia is stepping into the desktop PC chip market with its new GB10 Grace Blackwell platform, aiming squarely at AI workloads. Asus is taking the lead by launching systems based on this platform starting July 22. At this launch, Asus will also bring back its Ascend GX10 mini-PC. However, the exact timing for availability and pricing isn't fully detailed yet -- though Nvidia has shared some information in the past. The GB10 is quite a unique system-in-package combining a 20-core CPU and a powerful GPU designed specifically for AI tasks. The CPU part includes 10 high-performance Arm Cortex-X925 cores running up to 3.9 GHz, paired with 10 energy-efficient Cortex-A725 cores. On the GPU side, there's Nvidia's Blackwell architecture, capable of delivering 1 PetaFLOPS of FP4 compute power, optimized for artificial intelligence workloads like large language models and generative AI. One of the key strengths of the GB10 platform is its unified memory system. It features 128GB of LPDDR5X memory on a 256-bit interface, providing up to 273 GB/s bandwidth. This is comparable to the memory system found in Apple's M4 Pro chip, highlighting its capability for handling large, memory-intensive AI models efficiently. Nvidia positions this chip as a solution that brings data center-level AI performance into a compact desktop or edge device. Asus's Ascend GX10 mini-PC will serve as a showcase for this platform, targeting AI researchers, developers, and professionals needing powerful AI workstations in a smaller form factor. It's expected to be similar to Nvidia's DGX Spark system, which is priced around $3,000, though the exact cost of Asus's version hasn't been officially announced. Other major PC manufacturers like Dell, HP, and Lenovo are also preparing their versions of DGX Spark systems based on the same Nvidia platform. Details on their pricing and release dates are still under wraps, but these efforts indicate Nvidia's plan to establish this architecture broadly across AI-focused desktop workstations. Performance-wise, some leaked Geekbench results show the GB10's general compute power falls close to Qualcomm's Snapdragon X Elite and Apple's M3 processor. While this might seem underwhelming in raw CPU benchmarks, it's important to remember this chip's main focus is AI workloads where GPU compute and unified memory architecture play a larger role. Nvidia highlights the system's strong single-thread CPU performance, massive FP4 throughput on the GPU, and unified memory as key advantages over traditional CPU-GPU setups. Source: Tomshardware

ASUS's new Ascent GX10 with GB200 Blackwell Superchip launches July 22, its new AI Mini-PC

As an Amazon Associate, we earn from qualifying purchases. TweakTown may also earn commissions from other affiliate partners at no extra cost to you. ASUS has confirmed that its new AI supercomputer, the Ascent GX10, will be launching on July 22. The new ASUS Ascent GX10 is powered by NVIDIA's new GB200 Grace Blackwell Superchip, and acts as a powerful AI workstation that sits on your desk. The new ASUS Ascent GX10 is a small Mini-PC workstation that is tailored towards AI development and inference workloads, packing NVIDIA's new Grace CPU and Blackwell GPU inside of a unified GB200 Grace Blackwell Superchip. The Ascent GX10 will be configured with 128GB of LPDDR5X memory, PCIe Gen5 connectivity, NVMe SSD, and a custom cooling solution. The bigger news here about the launch of the ASUS Ascent GX10 system is that this is NVIDIA's first serious foray into the desktop CPU business, and while it's not a regular x86-based processor, the Grace CPU is an Arm-based processor that is normally aimed at the HPC and server workload space. However, the integration of the Arm-based Grace CPU in the ASUS Ascent GX10 will be used by developers and AI researchers needing edge AI compute, all without relying on traditional x86-based platforms. ASUS's new Ascent GX10 workstation AI system will compete against the likes of systems powered by AMD's new Ryzen AI Max 300 series "Strix Halo" APUs and Apple's Mac Studio. It won't be the only one, but for AI developers this is going to be a popular system, and it gives NVIDIA the chance to test its Grace Blackwell Superchip some testing in the real world.