GPUs & AI compute
Data-center GPUs and rack-scale AI systems — NVIDIA GB300 NVL72, HGX B200, and HGX H100, new and integration-ready.
NVIDIA
NVIDIA GB300 NVL72 (Supermicro MGX)
Rack-scale NVIDIA GB300 NVL72 in a single 19" Supermicro MGX rack — 72 Blackwell Ultra GPUs and 36 Grace CPUs, fully integrated and liquid-cooled.
NVIDIA
NVIDIA GB300 NVL72 (Lenovo 48U MGX)
NVIDIA GB300 NVL72 rack-scale system built on the Lenovo 48U MGX reference rack — 72 Blackwell Ultra GPUs, factory-integrated with direct water cooling.
NVIDIA
NVIDIA GB300 NVL72 (HPE 48U MGX)
NVIDIA GB300 NVL72 rack-scale system factory-integrated by HPE in a 48U liquid-cooled MGX-compliant rack — 72 Blackwell Ultra GPUs, 36 Grace CPUs.
NVIDIA
NVIDIA HGX B200 (Lenovo ThinkSystem SR780a V3)
NVIDIA HGX B200 8-GPU Blackwell server on the Lenovo ThinkSystem SR780a V3 — 1,440 GB HBM3e per node with Lenovo Neptune liquid cooling.
NVIDIA
NVIDIA HGX H100 80GB — Liquid-Cooled (Supermicro 4U H13)
NVIDIA HGX H100 8-GPU server on the Supermicro 4U H13, liquid-cooled — 8× H100 80GB SXM5 with AMD EPYC Genoa and ConnectX-7 NDR400 networking.
NVIDIA
NVIDIA HGX H100 80GB — Air-Cooled (Supermicro 8U H13)
NVIDIA HGX H100 8-GPU server on the Supermicro 8U H13, air-cooled — 8× H100 80GB SXM5 with AMD EPYC Genoa, for standard air-cooled facilities.