ASUS AI POD XA GB721-E2 NVIDIA GB300 NVL72 Rack-Scale AI Supercomputer - 72 Blackwell Ultra GPUs, 36 Grace CPUs, Liquid Cooled

SKU: XA GB721-E2 Brand: Asus

Pricing available upon request

Email sales@sourceit.com.sg or use Request for Quotation below and our team will confirm the latest price, availability and lead time.

Why buy from SourceIT

Authorised resellerGenuine stock with full manufacturer warranty.

Local supportSingapore-based warranty and technical assistance.

Procurement readyGeBIZ, Vendors@Gov, SAP Ariba, InvoiceNow and PEPPOL.

Bulk & export ordersVolume pricing and international delivery on request.

PRODUCT DESCRIPTION

ASUS AI POD XA GB721-E2 NVIDIA GB300 NVL72 Rack-Scale AI Supercomputer, 72 NVIDIA Blackwell Ultra GPUs, 36 NVIDIA Grace CPUs, 5th-Gen NVLink, ConnectX-8 SuperNIC, BlueField-3 DPU, 48U MGX Rack, Liquid Cooled (XA GB721-E2)

ASUS AI POD with NVIDIA GB300 NVL72: Built for AI Reasoning

The ASUS XA GB721-E2 is the ASUS AI POD full-rack system built on NVIDIA GB300 NVL72. It combines 72 NVIDIA Blackwell Ultra GPUs and 36 NVIDIA Grace CPUs in a liquid-cooled, 48U NVIDIA MGX-compliant rack with 18 compute trays and nine NVLink switch trays, engineered for trillion-parameter AI reasoning, LLM training and inference.

SourceIT supplies the ASUS XA GB721-E2 in Singapore as a project sale: site readiness, configuration, delivery and ASUS professional services are scoped and quoted per deployment.

One NVLink Domain at 1.8 TB/s

Fifth-generation NVIDIA NVLink links every GPU in the rack at 1.8 TB/s, so 72 GPUs work as one unified, high-bandwidth fabric. NVIDIA rates GB300 NVL72 at 1.5x the AI performance of GB200 NVL72.

ConnectX-8 SuperNICs and BlueField-3 DPUs

NVIDIA ConnectX-8 SuperNICs with NVIDIA Quantum-X800 InfiniBand or Spectrum-X Ethernet provide low-latency scale-out to multi-rack clusters, with BlueField-3 DPUs for accelerated data movement.

Liquid-to-Air or Liquid-to-Liquid Cooling

Manifold-based liquid cooling is offered in liquid-to-air and liquid-to-liquid designs, so the rack can be matched to data halls with or without facility water.

Rapid Deployment with ACC and AIDC

ASUS Control Center (ACC) and ASUS Infrastructure Deployment Center (AIDC) provide zero-touch onboarding, centralized configuration and rack-scale deployment automation, and ASUS backs the rack with end-to-end design, integration and lifecycle services.

ASUS XA GB721-E2 Datasheet - Technical Specifications

General

Product Name	ASUS AI POD with NVIDIA GB300 NVL72
Model	XA GB721-E2
Platform	NVIDIA GB300 NVL72 (Grace Blackwell Ultra)
Form Factor	48U NVIDIA MGX-compliant rack
Warranty	Per ASUS quotation and support contract

Compute

GPUs per Rack	72 x NVIDIA Blackwell Ultra
CPUs per Rack	36 x NVIDIA Grace
Compute Trays	18
NVLink Switch Trays	9
GPU-to-GPU Interconnect	Fifth-generation NVIDIA NVLink, 1.8 TB/s
Serviceability	Blackwell Ultra GPU SXM7 and SOCAMM module design

Networking

SuperNIC	NVIDIA ConnectX-8, 800 Gb/s per GPU
DPU	NVIDIA BlueField-3
Cluster Fabric	NVIDIA Quantum-X800 InfiniBand or Spectrum-X Ethernet

Cooling, Power and Management

Cooling	Manifold-based liquid cooling; liquid-to-air or liquid-to-liquid
Power	Rack-level busbar power; power shelf count and redundancy confirmed at quotation
Management Software	ASUS Control Center (ACC), ASUS Infrastructure Deployment Center (AIDC)
Rack Dimensions and Weight	See ASUS datasheet; confirmed at quotation

Compatibility & Software Support

NVIDIA AI Software

The system runs the NVIDIA accelerated computing stack, including CUDA, NVIDIA AI Enterprise, NIM microservices and NGC containers for arm64.

Arm64 Architecture

The Grace CPU is an Arm Neoverse V2 processor, so operating system and container images are arm64 builds. Check any x86-only commercial software before ordering.

ASUS AI POD Ecosystem

ASUS offers storage, networking, cooling and management as part of the AI POD, using validated reference architectures for predictable performance and simpler scaling.

Site Requirements & Ordering Information

What to Plan For

High-density three-phase power for a rack in the 130 kW class
Facility water loop for liquid-to-liquid cooling, or space and airflow for liquid-to-air units
Floor loading, delivery path and lift access for a fully populated 48U rack
Cluster fabric, storage and management networks

How This Is Sold

The price shown is an indicative price for one rack. Final pricing depends on configuration and services and is confirmed by formal quotation. Email sales@sourceit.com.sg for configuration, lead time and a GST quotation.

For deskside AI systems, see the NVIDIA DGX Spark & DGX Station collection.

Datasheet & Downloads

Frequently Asked Questions - ASUS XA GB721-E2

What is the ASUS XA GB721-E2?

The ASUS AI POD rack built on NVIDIA GB300 NVL72: 72 Blackwell Ultra GPUs and 36 Grace CPUs in a liquid-cooled 48U rack.

How is it different from the ASUS ESC NM2N721-E1?

The ESC NM2N721-E1 is the earlier GB200 NVL72 rack with Blackwell GPUs. The XA GB721-E2 uses Blackwell Ultra GPUs on the GB300 NVL72 platform.

Does it need facility water?

Not always. ASUS offers liquid-to-liquid cooling for sites with facility water and liquid-to-air cooling for sites without.

How do I buy it in Singapore?

Email sales@sourceit.com.sg. SourceIT will arrange sizing, site readiness and a formal quotation.