FLAGSHIP / BLACKWELL
Supermicro SYS-521GE-TNRT · 5U
RTX PRO 6000 AI Server
A configurable foundation for AI inference, private AI, visualization, and mixed enterprise workloads.
8× 96 GB GDDR7 ECCPCIe Gen 5
Explore system
ACCELERATED AI / HOPPER
HGX reference: SYS-821GE-TNHR · 8U
NVIDIA H200 Systems
High-bandwidth HBM3e platforms for demanding AI training, inference, and scientific computing.
141 GB HBM3e / GPUHGX / NVL
Explore system
CONFIGURED FOR YOUR WORKLOAD
Your requirements. Your configuration.
Custom AI & HPC Servers
Right-size compute, memory, networking, and cooling for a single system or a phased rack deployment.
Multi-GPU configurationsECC memory
Explore system
MGX or HGX?
MGX is a modular server design approach. HGX is an integrated multi-GPU platform. The right choice depends on your accelerator and interconnect requirements.
Need a different configuration?
Bring your bill of materials, workload profile, or rack deployment plan. We can start with any of them.