HPE NVIDIA GB300 NVL72 by HPE vs Inventec Artemis II Rack
Both are built on the NVIDIA GB300 NVL72 baseboard, so their accelerator performance is identical rather than merely similar. The choice between them is chassis, cooling, expansion and supplier, not FLOPS.
What actually differs
| Specification | HPE NVIDIA GB300 NVL72 by HPE | Inventec Artemis II Rack |
|---|---|---|
| Vendor | HPE | Inventec |
| Part number | S6C60A | — |
| Form factor | rack | rack |
| Released | — | — |
| Accelerator | 72x GB300 | 72x GB300 |
| Aggregate memory | — | — |
| Aggregate bandwidth | — | — |
| System power | 132.0 kW | 136.0 kW |
| Interconnect | Fifth-generation NVLink across all 72 GPUs through nine NVLink switch trays; each compute tray carries two ConnectX-8 ports at 800 Gbps and one BlueField-3 DPU, with two Spectrum SN2201 top-of-rack switches for management | NVLink across all 72 GPUs over passive copper cable cartridges, with nine 1RU NVLink switch trays; scale-out is ConnectX-8 at 800 Gb/s InfiniBand east-west, carried on two I/O boards holding two SuperNICs each, plus a BlueField-3 DPU at 400 Gb/s north-south |
Rows shown in grey are identical between the two.
HPE NVIDIA GB300 NVL72 by HPE
HPE's build of NVIDIA's GB300 NVL72, a 48U rack holding 36 Grace processors and 72 Blackwell Ultra GPUs across eighteen compute trays, each tray carrying two Grace CPUs and four GPUs on two GB300 boards. Nine NVLink switch trays tie the 72 GPUs into one domain over fifth-generation NVLink, and each tray adds two ConnectX-8 ports at 800 Gbps and a BlueField-3 DPU. Power comes from eight 33 kW shelves onto a 50 V DC busbar, each shelf built from six 5.5 kW supplies. HPE is unusually precise about what the rack actually draws: 132 kW nominal thermal design power, around 155 kW electrical design power at peak, and a recommendation that data centres provision busways for 192 kW. The figure shown here is the 132 kW nominal. Cooling is direct liquid to cold plates on both CPUs and GPUs, fed by an in-row CDU rated at 1.3 MW that can serve up to eight racks. The rack measures 2495 by 600 by 1068 mm and weighs about 3,300 lb fully loaded. HPE publishes no accelerator memory total and no throughput figure; the only memory it states is 512 GB of LPDDR5X per Grace CPU, which is host memory rather than HBM.
Vendor product pageInventec Artemis II Rack
The Blackwell Ultra generation of Inventec's Artemis rack, built on the NVIDIA GB300 NVL72 and the MGX platform, again pairing 36 Grace CPUs with 72 Blackwell GPUs across eighteen compute trays and nine NVLink switch trays in a 48RU rack. The change from the first Artemis is in the network: east-west moves from ConnectX-7 at 400 Gb/s to ConnectX-8 at 800, carried on two dedicated I/O boards with two SuperNICs apiece, so back-end bandwidth keeps pace with the GPUs. Cooling narrows to row-based and sidecar, with leakage detection, and Inventec rates the rack at a maximum of 136 kW. No throughput or memory figures are published. This entry links to no reference design because the only GB300 NVL72 record in this catalogue is NVIDIA's own DGX appliance, which is a finished competing product rather than a reference platform.
Vendor product page