ASUS announced the showcase of ExpertCenter Pro ET900N G3 at CES 2026, underscoring its commitment to delivering enterprise-grade AI infrastructure in accessible, deskside form factors. The all-new ET900N G3 accelerated by the NVIDIA GB300 Grace Blackwell Ultra Desktop Platform sets a new standard for deskside AI supercomputers, combining extreme performance, unified memory architecture, and data-center-class connectivity.
Solving the last-mile challenge of modern AI development
AI development has reached extraordinary heights through massive cloud and data-center infrastructure, yet many researchers, developers, and data scientists still face a ‘last-mile’ challenge. While cloud services offer immense scale, countless workflows require local, private, and immediate compute power — especially for training, fine-tuning, or running large AI models that exceed the limits of traditional workstations. What these professionals need is a system that delivers data-center-class performance in a familiar, easily deployable deskside form factor.
Bringing data-center-class compute into a unified desktop platform
ExpertCenter Pro ET900N G3 represents a new generation of deskside AI supercomputers built to bridge this gap. Accelerated by the NVIDIA GB300 Grace Blackwell Ultra Desktop Platform, ET900N G3 pairs a NVIDIA Grace CPU and NVIDIA Blackwell Ultra GPU over NVIDIA NVLink-C2C high-bandwidth, low-latency chip-to-chip interconnect, enabling petaflop-scale accelerated computing in a standalone deskside AI supercomputer.
With 775GB of coherent unified memory, ET900N G3 offers more than double the GPU memory of a four-GPU workstation — empowering developers to run larger models, accelerate experimentation, and bring generative AI capabilities directly to the desktop.
DGX architecture tailored for next-generation AI workloads
Designed from the ground up for local AI workloads, ExpertCenter Pro ET900N G3 is one of the first systems based on NVIDIA DGX Station architecture to reach the deskside market. Its massive memory pool and powerful NVIDIA Grace CPU and NVIDIA Blackwell Ultra GPU compute engine make it ideal for large-scale model training and inference — including LLMs, advanced simulations, multi-modal AI, and deep learning research. Paired with the NVIDIA AI software stack, ET900N G3 offers a turnkey development environment optimized for data science, machine learning, and analytics, with the ability to be interconnected to expand its supercomputing power twofold when needed.
Supercomputer-level capability made accessible for innovators
ExpertCenter Pro ET900N G3 provides a critical middle ground: the power of a supercomputer without the complexity of server infrastructure. This enables businesses, research institutes, and advanced creators to adopt AI workflows more rapidly and more securely, using a system engineered specifically to meet the demands of modern AI development.
This powerful new supercomputer marks a major leap forward in accessible AI supercomputing, delivering exceptional performance, massive coherent memory, and enterprise-grade software integration in a deskside system. As AI model sizes grow and real-time, private compute becomes essential, ExpertCenter Pro ET900N G3 brings the power of a data center directly to the professionals who need it most — unlocking new possibilities for innovation, research, and next-generation AI development.
Availability & Pricing
ASUS ExpertCenter Pro ET900N G3 is expected to be available worldwide in late Q1 2026. However, the product roadmap for India is still awaited.
