ASUS Unveils ExpertCenter Pro ET900N G3: A Desktop Powerhouse with NVIDIA's GB300 Blackwell Ultra Superchip

ASUS brings Nvidia's GB300 Blackwell Ultra 'desktop superchip' to workstations -- features up to 784GB of coherent memory, 20 PFLOPS AI performance

Asus has quietly launched the ExpertCenter Pro ET900N G3, one of the first desktop systems powered by Nvidia's GB300 Grace Blackwell Ultra "desktop superchip." This marks a notable shift for Nvidia, which has historically reserved its highest-end AI hardware for its own DGX Station lineup. With Blackwell Ultra, the company is partnering with OEMs like Asus, Lambda, and others to bring AI-focused workstations to a broader market. The GB300 Desktop Superchip combines a Grace ARM-based CPU with Nvidia's new Blackwell Ultra GPU -- the same pairing that powers the DGX Station announced earlier this year at GTC 2025. This platform delivers up to 784 GB of unified LPDDR5X and HBM3E memory and next-gen Tensor Cores with enhanced FP4 precision, making it ideal for AI training, inference, and large-scale model development. Asus's ExpertCenter mirrors these design principles with 20 PFLOPS of AI performance, ConnectX-8 SuperNIC networking (800 Gb/s) for high-speed scaling, and support for Nvidia DGX OS. Moreover, this unassuming-looking desktop offers serious expandability: three PCIe x16 slots for additional GPUs or accelerators, three M.2 slots for SSD storage, and power delivery via standard ATX + EPS12V connectors, plus three 12V-2×6 connectors capable of delivering up to 1,800W to the GPU alone. In theory, users could stack additional RTX Blackwell cards to further increase compute power. While Nvidia has not revealed complete GB300 specifications or pricing, SXM-based compute GPUs alone cost tens of thousands of dollars, putting both the DGX Station and ExpertCenter in the five-digit range. The ExpertCenter G3 arrives at a time when Nvidia's GB300 Blackwell Ultra is scaling across the AI industry. Dell recently deployed the first GB300 NVL72 clusters at CoreWeave, featuring 72 Blackwell Ultra GPUs and 36 Grace CPUs per rack, with 1.1 exaFLOPS of FP4 inference performance -- 50% more than the GB200 NVL. Volume shipments of GB300 servers are reportedly expected to ramp up by September 2025. Rumors indicate Nvidia's decision to reuse the Bianca motherboard design from GB200 has eased supply chain bottlenecks and accelerated production. Interestingly, Asus also introduced the Ascent GX10, a compact desktop based on the smaller GB10 Grace Blackwell platform. While not as powerful as the GB300-equipped ExpertCenter, the GX10 hints at Nvidia's intent to bring its AI hardware into more accessible form factors. This launch aligns with Nvidia's strategy of collaborating with OEMs like Asus, Dell, and Lambda to move beyond the exclusive DGX lineup, making high-performance AI systems available to a broader range of professionals. With the rapid evolution of AI hardware, these partnerships could pave the way for consumer-facing AI workstations, especially as future platforms like Rubin push GPU density, power efficiency, and thermal design to new levels. With Asus joining forces with Nvidia's Blackwell Ultra push, the ExpertCenter Pro ET900N G3 is more than just another AI workstation -- it signals Nvidia's growing ambitions beyond GPUs. While AMD and Intel have long dominated the CPU landscape, Nvidia is edging into their territory with the ARM-based Grace processor, built specifically for AI and HPC workloads rather than as a direct x86 competitor. Grace isn't designed to replace general-purpose CPUs; instead, it complements Nvidia's GPU dominance by enabling unified, high-bandwidth memory and compute performance that traditional setups can't easily match. This doesn't put Nvidia in a head-to-head battle with AMD and Intel -- at least not yet -- but it does carve out a segment of the market that could gradually erode their share in AI-focused servers and workstations.

ASUS intros ExpertCenter desktop PC powered by NVIDIA GB300 Blackwell Ultra , up to 784GB RAM

TL;DR: ASUS launched the ExpertCenter Pro ET900N G3, its first desktop with NVIDIA's GB300 Grace Blackwell Ultra Superchip, delivering 20 PFLOPS AI performance. Featuring up to 784GB unified memory, advanced Tensor Cores, high-speed ConnectX-8 networking, and extensive expandability, it's ideal for AI training and large-scale model deployment. ASUS has just launched its ExpertCenter Pro ET900N G3: its first desktop system powered by NVIDIA's new GB300 Grace Blackwell Ultra Desktop Superchip. Check it out: The new NVIDIA GB300 Grace Blackwell Desktop Superchip combines the Grace Arm-based CPU with NVIDIA's new GB300 Blackwell Ultra GPU, the same hardware combination that powers the new DGX Station announced earlier this year at GTC 2025. We have up to 784GB of unified LPDDR5X and HBM3E memory inside of the new ASUS ExpertCenter Pro ET900N G3 system, with next-gen Tensor Cores with enhanced FP4 precision, making the ASUS ExpertCenter Pro ET900N G3 desktop supercomputer perfect for AI training, inference, and large-scale model deployment. ASUS's new ExpertCenter Pro ET900N G3 has the same design principles with 20 PFLOPS of AI performance, ConnectX-8 SuperNIC networking (800Gb/s) for high-speed scaling, and support for NVIDIA DGX OS. This system has some major expandability as well, with 3 x PCIe x16 slots for more GPUs or AI accelerators, 3 x M.2 SSD slots for additional storage, and power delivery through the standard ATX + EPS12V connectors, backed up by 3 x 12V-2x6 power connectors that provide up to 1800W to the GPUs alone. This means that you could stack additional RTX Blackwell AI GPUs to boost compute performance, as you've got the space and power at the ready inside of the ASUS ExpertCenter Pro ET900N G3 desktop supercomputer. Don't expect the ASUS ExpertCenter Pro ET900N G3 desktop AI supercomputer to be cheap, but we should have pricing unveiled very shortly as ASUS has it out in the wild.

ASUS Deploys NVIDIA's Most Powerful GB300 Superchip Inside A Regular Desktop Chassis; Up To 20 PFLOPS Of AI Performance On Your Desk

The server-specific Blackwell superchip gets a place inside a regular desktop PC case, offering leading AI performance of up to 20 PFLOPS. With the introduction of NVIDIA's leading superchip in the Blackwell family, various hardware manufacturers have shown their interest in deploying it in their custom AI machines. The GB300 Blackwell superchip not only allows enterprises to scale their servers with the incredibly powerful combo of Grace CPU and B300 GPU, but it also allows manufacturers to design custom PCs that can be used similar to a regular desktop. If you don't know what a powerful supercomputer looks like with the GB300 superchip, then ASUS has one for you. The company silently introduced its newest supercomputer, called ExpertCenter Pro E900N E3, which looks like a regular desktop inside a mid-tower but is actually one of the fastest desktops ever made. Packed with the GB300 platform, the computer brings extremely fast compute performance, specialized for AI tasks like Large Language Models, Deep Learning Training, Scientific Computing, etc. The supercomputer brings a 784 GB Coherent memory, which comes as a result of 496 GB LPDDR5X memory chips that surround the Grace CPU and 288 GB HBM3E memory for the Blackwell GPU. The system delivers up to 20 PFLOPS of AI performance, brings the ConnectX-8 SuperNIC for 800 GB/s networking bandwidth, and uses the NVIDIA DGX OS system. The computer also allows decent upgradeability since the motherboard has three PCIe x16 slots, which can be used for adding more GPUs and for storage, it brings three M.2 slots for fast NVMe SSDs. Compared to the regular mainstream motherboards, this one is a lot different and has triple 16-pin power connectors onboard, which can deliver up to 1800W of power. Remember that this computer brings just a single GB300 superchip, which already has immense potential, but NVIDIA also offers the GB300 NVL72 rack, which exponentially increases the performance through deploying 72 Blackwell Ultra GPUs and 36 NVIDIA Grace CPUs. With such an incredible configuration, the total Coherent memory comes close to 40 TB, and the FP4 compute performance reaches up to 1.4 Exaflops. Nonetheless, those are specialized for servers, but businesses that want powerful computing on their desks, the ExpertCenter Pro ET900N G3 is plenty for intensive tasks. ASUS hasn't revealed its official price tag, but such systems cost thousands of dollars easily.