Gigabyte G593-SD1-LAX3 vs NVIDIA HGX H200
Accelerator configuration, aggregate memory, bandwidth and power, side by side.
Specifications
| Specification | Gigabyte G593-SD1-LAX3 | NVIDIA HGX H200 |
|---|---|---|
| Vendor | Gigabyte | NVIDIA |
| Part number | 6NG593SD1DR000LBX3 | — |
| Form factor | rack | baseboard |
| Released | 2024 | 2024 |
| Accelerator | 8x H200 | 8x H200 |
| Aggregate memory | 1.1 TB | 1.1 TB |
| Aggregate bandwidth | 38.4 TB/s | 38.4 TB/s |
| System power | — | 8.0 kW |
| Interconnect | NVIDIA NVLink with NVSwitch, 900 GB/s GPU-to-GPU | NVSwitch + NVLink |
Rows shown in grey are identical between the two.
Gigabyte G593-SD1-LAX3
A 5U direct-liquid-cooled server carrying the NVIDIA HGX H200 baseboard with eight SXM GPUs, connected at 900 GB/s by NVLink and NVSwitch. Both CPUs and GPUs are liquid cooled, which is what lets Gigabyte fit the platform into 5U rather than the 8U an air-cooled equivalent needs. Two LGA 4677 sockets take 5th or 4th generation Intel Xeon Scalable processors or the Xeon CPU Max series, with 32 DIMM slots across eight DDR5 channels, eight Gen5 NVMe bays, twelve PCIe Gen5 x16 slots and BlueField-3 DPU compatibility. Power comes from four plus two redundant 3000 W Titanium supplies. It weighs 91 kg net and orders as 6NG593SD1DR000LBX3. Note that Gigabyte's page quotes "over 32 petaflops of FP8 deep learning compute" for an eight-way HGX H200; that is NVIDIA's own marketing figure for the baseboard rather than a Gigabyte measurement, and it is the sparse number. The dense figures shown here are NVIDIA's for the same baseboard, and they are what this site publishes throughout.
Vendor product pageNVIDIA HGX H200
HGX platform for cloud providers with H200 GPUs
Vendor product page