Hewlett Packard Enterprise · ProLiant
ProLiant Compute DL380a Gen12
Accelerator-optimized 4U server with up to ten double-wide GPUs for cost-effective enterprise AI inferencing.
| OEM | Hewlett Packard Enterprise |
|---|---|
| Family | ProLiant |
| Generation | Gen12 |
| Released | 2024 |
| Form factor | Rack 4U |
| Processor sockets | 2 |
| Processor | Intel Xeon 6 (E-core / P-core) |
| Max cores per CPU | 144 |
| Max cores per server | 288 |
| Max CPU TDP | 350 W |
| DIMM slots | 32 |
| Memory type | DDR5, up to 6400 MT/s |
| Max memory | 8 TB |
| Drive bays | Up to 8 SFF NVMe or 16 EDSFF drives |
| Max NVMe / 3.5" bays | 16 / 0 |
| GPUs | Up to 10 double-wide GPUs (L40S, H100 NVL, H200 NVL), 8 RTX PRO 6000 Blackwell, or 16 single-wide L4 |
| PCIe slots | ? (PCIe Gen5) |
| OCP 3.0 slots | 2 |
| Power supplies | up to 3,200 W, redundant |
| Management | iLO 7 |
| Suited to | AI inference, AI training, VDI, HPC |
Official sources:
https://www.hpe.com/us/en/compute/hpe-proliant-compute/dl380a-gen12.html ↗
Spec sheet: https://www.hpe.com/psnow/doc/a00047453enw ↗