This 2U GPU server, based on NVIDIA MGX™ architecture, is built for large-scale AI training, HPC workloads, and data-intensive computing. Supporting a single Intel Xeon 6500P or 6700P-series processor with up to 136 PCIe lanes, it enables high-bandwidth communication between CPU, GPUs, and storage. With support for up to four NVIDIA H200 NVL or RTX Pro 6000 Blackwell Server Edition GPUs, it delivers powerful parallel compute capabilities for deep learning and simulation workloads.
The platform features 16 DDR5 RDIMM slots across 8 memory channels, high-speed PCIe 5.0 expansion, and NVMe-based storage for fast data throughput. Enterprise-grade management with IPMI, Redfish, dual BIOS, and hardware root of trust ensures system stability, security, and scalability in production environments.
Configure Now