Product

GIGABYTE G593-SD0-AAX1

Part number G593-SD0-AAX1

Price
USD $100
Stock
1

5U dual-socket Intel Xeon server built around an NVIDIA HGX H100 eight-GPU SXM5 module, with 900 GB/s NVLink/NVSwitch bandwidth, twelve Gen5 x16 low-profile slots, and 4+2 3000 W Titanium power supplies.

  • NVIDIA HGX H100 with eight SXM5 GPUs
  • 900 GB/s GPU-to-GPU bandwidth with NVLink and NVSwitch
  • Dual 4th/5th Gen Intel Xeon Scalable or Xeon Max processors
  • 12 low-profile PCIe Gen5 x16 slots plus one Gen4 x16 slot
  • 4+2 3000 W 80 PLUS Titanium redundant power supplies

Request a Quote

Specifications

Model G593-SD0-AAX1
GPU Model NVIDIA HGX H100
GPU Count 8 SXM5
Form Factor 5U rackmount
Cooling Air-cooled chassis
GPU Interconnect NVLink and NVSwitch, 900 GB/s GPU-to-GPU
CPU Dual 5th/4th Gen Intel Xeon Scalable or Intel Xeon CPU Max Series, TDP up to 350 W
Socket / Chipset 2 × LGA 4677; Intel C741
Memory 32 × DDR5 RDIMM, 8-channel per CPU; up to 5600 MT/s (5th Gen, 1DPC)
Storage 8 × 2.5-inch Gen5 NVMe/SATA/SAS-4 hot-swap bays
Networking 2 × 10 Gb/s LAN (Intel X710-AT2) plus management LAN
Expansion 12 × LP PCIe Gen5 x16; 1 × LP PCIe Gen4 x16
Power 4+2 3000 W 80 PLUS Titanium redundant PSUs
Management ASPEED AST2600 BMC
Dimensions 5U, 447 × 219.7 × 945 mm
Operating Temperature 10°C to 35°C
Official Ordering Number 6NG593SD0DR000ABX1* (5th/4th Gen); 6NG593SD0DR000AAX1* (4th Gen)

Description

The GIGABYTE G593-SD0-AAX1 is a 5U dual-processor GPU server built around an NVIDIA HGX H100 module with eight SXM5 GPUs. Gigabyte documents 900 GB/s of GPU-to-GPU bandwidth with NVLink and NVSwitch, and lists NVIDIA-Certified data-center server status. It shares the G593 5U mechanical outline with the G593-SD1 H200 system, but the GPU board is HGX H100 rather than HGX H200.

The host supports dual 4th or 5th Generation Intel Xeon Scalable processors or Intel Xeon CPU Max Series, with a CPU TDP of up to 350 W, two LGA 4677 sockets, and the Intel C741 chipset. Memory is 32 DDR5 RDIMM slots, eight channels per CPU. Front storage is eight 2.5-inch Gen5 NVMe/SATA/SAS-4 hot-swap bays. A notable difference from the SD1 variant is the I/O complement: twelve low-profile PCIe Gen5 x16 slots plus one low-profile PCIe Gen4 x16 slot, described as a four-root-port design. Onboard networking is two 10 Gb/s ports via Intel X710-AT2, with management LAN and an ASPEED AST2600 BMC. Gigabyte also lists compatibility with NVIDIA BlueField-2 DPUs.

Power is 4+2 3000 W 80 PLUS Titanium redundant supplies. Chassis dimensions are 447 × 219.7 × 945 mm, and the operating temperature range is 10°C to 35°C. Official ordering numbers are 6NG593SD0DR000ABX1* for the 5th/4th Gen barebone with the NVIDIA module, and 6NG593SD0DR000AAX1* for the 4th Gen package. The model name used as the part number on this page is G593-SD0-AAX1.

Use this system when you need an eight-GPU HGX H100 training or inference node on Intel Xeon. GPU-level H100 SXM parameters are listed on the related NVIDIA H100 80GB SXM5 page. Request a quote with the CPU, memory, storage, and network configuration you require.

  • NVIDIA H100 80GB SXM5

    NVIDIA H100 80GB SXM5

    P/N NVIDIA H100 80GB SXM5

    Price USD $100 Stock 1

    Hopper-architecture SXM accelerator with 80 GB of HBM3 memory, fourth-generation NVLink, and a configurable TDP up to 700 W, built for dense HGX training and inference nodes.

    GPU Model
    NVIDIA H100 80GB SXM5
    Form Factor
    SXM5
    GPU Count
    1
    GPU Memory
    80 GB HBM3

    Request a Quote View details

  • GIGABYTE G593-SD1-AAX3

    GIGABYTE G593-SD1-AAX3

    P/N G593-SD1-AAX3

    Price USD $100 Stock 1

    5U dual-socket Intel Xeon server built around an NVIDIA HGX H200 eight-GPU SXM module, with 900 GB/s NVLink/NVSwitch bandwidth and 4+2 3000 W Titanium power supplies.

    Model
    G593-SD1-AAX3
    GPU Model
    NVIDIA HGX H200
    GPU Count
    8 SXM
    Form Factor
    5U rackmount

    Request a Quote View details

Ready to specify a configuration?

Share the use case, the target build, quantity, destination country, and timeline. We will take it from the inquiry.

Request a Quote