ASUS ExpertCenter Pro ET900N G3 NVIDIA Grace Blackwell 748GB Coherent

The ASUS ExpertCenter Pro ET900N G3 is a revolutionary deskside AI supercomputer engineered to deliver data centre class compute performance directly to your office environment. Serving as the ultimate computational centre for advanced AI developers and researchers, this tower workstation is powered by the groundbreaking NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip, combining a 72-core Arm Neoverse V2 CPU with a Blackwell Ultra GPU. Its crowning achievement is a massive 748GB of unified coherent memory (496GB LPDDR5X and 252GB HBM3e) linked via NVLink-C2C, ensuring that even trillion-parameter LLMs and intensive generative AI workloads remain perfectly stabilised during local training and inference. Beyond its sleek, unobtrusive colour aesthetic designed to seamlessly blend into professional enterprise spaces, the system allows organisations and busineesses to easily customise their storage configurations with 4TB of NVMe M.2 SSDs, with support for up to 8TB across cutting-edge PCIe 5.0 and 6.0 M.2 slots, with 4TB. Boasting dual NVIDIA ConnectX-8 QSFP ports for unprecedented 400G high-bandwidth connectivity, this 1600W powerhouse establishes an exceptionally secure scalable and stackable foundation, capable of driving the next generation of autonomous AI agents and complex simulations with an astonishing 20 PFLOPS of local performance.

Features

---

ExpertCenter Pro ET900N G3

Unleash Superior AI Power on Your Desktop - Your Trusted AI Supercomputer - Based on NVIDIA DGX™ Station Architecture

The ASUS ExpertCenter Pro ET900N G3 is part of a new class of deskside AI supercomputers. Designed from the ground up to build and run AI, this revolutionary system unleashes the NVIDIA® GB300 Grace Blackwell Ultra Desktop Superchip and a massive 748GB of large coherent memory, with future support planned for Windows-based AI development and agentic environments. Fully compatible with NVIDIA NemoClaw and NVIDIA AI Enterprise, it enables the local deployment of trillion-parameter models and autonomous AI agents at the deskside. Capable of developing and running large local AI training and inferencing workloads, this desktop system uses the NVIDIA® AI Software Stack to put an unprecedented amount of compute performance at the fingertips of AI development teams.

• Extreme AI Performance: Built on NVIDIA DGX Station™ architecture, powered by the NVIDIA® GB300 Grace Blackwell Superchip, with up to 20 petaFLOPS of AI performance and 748GB coherent memory.
• Open-Source Agent Ready: Supports NVIDIA® NemoClaw for secure, streamlined AI agent workflows.
• Full Stack AI Solution: Combines advanced hardware with the NVIDIA AI software stack for AI development and deployment.
• Scalable Architecture: NVIDIA® NVLink-C2C and ConnectX-8 networking enable greater memory capacity and model scalability.
• Tower Design, Advanced Performance: Delivers powerful AI compute in a standard tower form factor.

Applications - Powering AI Across Industries and Beyond

Automotive

Aerospace

Agentic AI

Healthcare & Medical Research

Smart Infrastructure

Agentic AI

Secure and Scalable Agentic AI with NVIDIA NemoClaw

The ASUS ExpertCenter Pro ET900N G3 with the NVIDIA NemoClaw open source stack, adds privacy and security controls to OpenClaw. NemoClaw installs NVIDIA OpenShell to enforce policy-based privacy and security guardrails, giving users control over how agents behave and handle data and provides the compute resources to run open models like NVIDIA Nemotron locally for enhanced privacy and cost efficiency.

Thermal

Extreme Cooling for Extreme AI Workloads

Features a data centre-grade thermal architecture designed to sustain extreme AI workloads without compromise. With optimised airflow, advanced heat dissipation, and precision thermal control, it efficiently supports next-generation deskside supercomputer performance for AI training and inference. This enables long-duration, full-load local AI computing with zero thermal throttling, consistent peak performance, and 24/7 reliability for mission-critical workloads.

Technological Breakthroughs

NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

The NVIDIA DGX Station features the NVIDIA Blackwell Ultra GPU connected to a high-performance NVIDIA Grace CPU using the NVIDIA NVLink®-C2C interconnect to deliver best-in-class system communication and performance.

NVIDIA Blackwell Generation Tensor Cores

NVIDIA DGX Station features NVIDIA Blackwell Generation Tensor Cores, enabling 4-bit floating point (NVFP4) AI. FP4 increases the performance and size of next-generation models that memory can support while maintaining high accuracy.

NVIDIA ConnectX-8 SuperNIC

The NVIDIA ConnectX®-8 SuperNIC™ supercharges hyperscale AI computing workloads. With up to 800 gigabits per second (Gb/s), ConnectX-8 SuperNIC delivers extremely fast, efficient network connectivity, and supports linking up to two DGX Stations to scale model capacity and performance even further.

Preconfigured AI Software Stack

DGX Station features an optimised, preconfigured operating system, Ubuntu with NVIDIA AI Developer Tools. This environment comes pre-installed with system-specific configurations and essential CUDA-X™ libraries, providing a seamless, full-stack foundation for accelerating AI development, data science, and local inference workloads.

NVIDIA NVLink-C2C Interconnect

NVIDIA NVLink-C2C extends the industry-leading NVLink technology to a chip-to-chip interconnect between the GPU and CPU, enabling high-bandwidth coherent data transfers between processors and accelerators.

Large Coherent Memory for AI

AI models continue to grow in scale and complexity. Training and running these models within NVIDIA Grace Blackwell Ultra’s large coherent memory allows for massive-scale models to be trained and run efficiently within one memory pool, thanks to the C2C superchip interconnect that bypasses the bottlenecks of traditional CPU and GPU systems.

Workload Optimised Power-Shifting

NVIDIA DGX Stations take advantage of AI-based system optimisations that intelligently shift power based on the currently active workload, continually maximising performance and efficiency.

NVID