ExpertCenter Pro ET900N G3
- 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.
ASUS ExpertCenter Pro
ET900N G3
Based on NVIDIA DGX™ Station
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 up to a massive 748GB of large coherent memory. Capable of developing and running large-scale 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.
Technological Breakthroughs
Grace Blackwell Ultra Superchip
Features an NVIDIA Blackwell Ultra GPU, which comes with the latest-generation NVIDIA CUDA® cores and fifth-generation Tensor Cores, connected to a high-performance NVIDIA Grace CPU via the NVIDIA® NVLink®-C2C interconnect, delivering best-in-class system communication and performance.
Fifth-Generation Tensor Cores
Powered by the latest NVIDIA Blackwell Generation Tensor Cores, enabling 4-bit floating point (FP4) 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 is optimized to supercharge hyperscale AI computing workloads. With up to 800 gigabits per second (Gb/s), NVIDIA ConnectX®-8 SuperNIC delivers extremely fast, efficient network connectivity, significantly enhancing system performance for AI factories.
NVIDIA DGX OS
NVIDIA DGX OS implements stable, fully qualified operating systems for running AI, machine learning, and analytics applications on the NVIDIA DGX platform. It includes system-specific configurations, drivers, and diagnostic and monitoring tools. Easily scale across multiple NVIDIA DGX Station systems, NVIDIA DGX Cloud, or other accelerated data center or cloud infrastructure.
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 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.
NVIDIA AI Software Stack
A full stack solution for AI workloads including fine-tuning, inference, and data science. NVIDIA’s AI software stack lets you work local and easily deploy to cloud or data center using the same tools, libraries, frameworks and pretrained models from desktop to cloud.
Workload Optimized Power-Shifting
NVIDIA DGX Stations take advantage of AI-based system optimizations that intelligently shift power based on the currently active workload, continually maximizing performance and efficiency. Large 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.
Specifications
Operating System
Ubuntu with NVIDIA AI Developer Tools
Processor / System Bus
Single NVIDIA Grace™ CPU Superchip with 72 Arm® Neoverse V2 cores
Single NVIDIA Blackwell Ultra GPU
Memory
748 GB of Coherent Memory
– CPU Memory 496GB LPDDR5X (396 GB/s)
– GPU Memory 252GB HBM3e (7.1 TB/s)
Expansion Slots
Total: 3
Location-1: PCIe x16 slots (Gen 5.0 x16)
Location-2: PCIe x16 slots (Gen 5.0 x8)
Location-3: PCIe x16 slots (Gen 5.0 x8)
Storage
Total: 4
2 x M.2 slot (Key M), type 2280 (supports PCIe 5.0 x4 mode, OS RAID 1 configuration)
2 x M.2 slot (Key M), type 2280 (supports PCIe 6.0 x4 mode, training data usage)
Networking
2 x NVIDIA ConnectX-8 SuperNIC QSFP112 ports*
1 x Marvell 10G Ethernet
1 x Realtek 1Gb Ethernet (Dedicated management LAN for BMC)
1 x M.2 slot (Key E)**
*QSFP Transceiver Required.
**Support Wi-Fi 7 (MediaTek MT7925B22M, Optional)
*** The Bluetooth® version may vary, please refer to the Wi-Fi module manufacturer’s website for the latest specifications.
Graphic
Supports up to one NVIDIA® graphics card on the first PCIe slot (Optional)
– NVIDIA® RTX PRO™ 4000 Blackwell SFF
– NVIDIA® RTX PRO™ 2000 Blackwell
Front I/O Ports
2 x USB 10Gbs Type-C ports
2 x USB 10Gbs ports
1 x USB 2.0 port
1 x Headphone port
1 x Microphone port
Rear I/O Ports
4 x USB 10Gbps ports (4 x Type-A)
1 x Micro USB COM port (for BMC)
2 x CX-8 NIC 400G QSFP ports
1 x Realtek 1Gb Ethernet port (for BMC)
1 x Marvell 10Gb Ethernet port
1 x mini DisplayPort (for BMC)
3 x Audio jacks
Switch/LED
Front:
1 x Power Button
1 x Storage Activity LED
1 x System Message LED
Rear:
2 x QSFP LAN Activity LEDs
2 x 10G LAN Message LED (Activity and Speed)
2 x 1G LAN Message LED (Activity and Speed)
Management Solution
ASPEED AST2600 with AMI MegaRAC based firmware supporting IPMI 2.0 and DMTF Redfish API
On-board TPM2.0
Dimensions
23.0” x 9.1” x 22.3” (584mm x 232mm x 565mm)
Weight
Net Weight : 27 kg
Gross Weight : 32 kg
Power Supply
1600W TITANIUM ATX Power Supply
(Power Supply/System Rating: 115-240Vac, 15A-8A, 50-60Hz)
*Power Cord: IEC C19 type (Optional)
– Maximum power output is optimized based on the regional input voltage and the power cord assembly.
**Operating Voltage & Regional Support
– North America: 125V AC (Cord: IEC C19 to NEMA 5-20P)
– Global: 200V – 240V AC (Cord: IEC C19 to Regional Standard Plug)
Environment
Operation temperature: 10℃ ~ 35℃
Non operation temperature: 5℃ ~ 40℃
Non operation humidity: 20% ~ 90% (Non condensing)
Optional Items
QSFP 400G Transceivers
Wi-Fi module & antenna