747-300-5288
Supermicro's deep learning optimized GPU servers designed for the modern data center.
Modular Building Block Design, Future Proof Open-Standards Based Platform in 4U, 5U, or 8U for Large Scale AI training and HPC Applications
NVIDIA HGX H100/A100 4-GPU/8-GPU, AMD Instinct MI300X/MI250 OAM Accelerator, Intel Data Center GPU Max Series
Intel® Xeon® or AMD EPYC™
Up to 32 DIMMs, 8TB
Up to 24 Hot-swap U.2 or 2.5″ NVMe/SATA drives
Direct-to-chip liquid-cooled systems for high-density AI infrastructure at scale.
NVIDIA HGX H100 4-GPU/8-GPUs
Maximum Acceleration and Flexibility for AI/Deep Learning and HPC Applications
Up to 10 NVIDIA H100 PCIe GPUs, or up to 10 double-width PCIe GPUs
Up to 32 DIMMs, 8TB DRAM or 12TB DRAM + PMem
Up to 24 Hot-swap 2.5″ SATA/SAS/NVMe
Modular Building Block Platform Supporting Today's and Future GPUs, CPUs, and DPUs
Up to 4 NVIDIA PCIe GPUs including H100, H100 NVL, and L40S
NVIDIA GH200 Grace Hopper™ Superchip, Grace™ CPU Superchip, or Intel® Xeon®
Up to 960GB integrated LPDDR5X memory (Grace Hopper or Grace CPU Superchip) or 16 DIMMs, 4TB DRAM (Intel)
Up to 8 E1.S + 4 M.2 drives
Multi-processor system combining CPU and GPU, Designed for the Convergence of AI and HPC
4 AMD Instinct MI300A Accelerated Processing Unit (APU)
AMD Instinct™ MI300A Accelerated Processing Unit (APU)
Up to 512GB integrated HBM3 memory (4x 128GB)
Up to 8 2.5″ NVMe or Optional 24 2.5″ SATA/SAS via storage add-on card + 2 M.2 drives
Flexible Design for AI and Graphically Intensive Workloads, Supporting Up to 10 GPUs
NVIDIA HGX A100 8-GPU with NVLink, or up to 10 double-width PCIe GPUs
Dense and Resource-saving Multi-GPU Architecture for Cloud-Scale Data Center Applications
Up to 3 double-width PCIe GPUs per node
Up to 8 DIMMs, 2TB per node
Up to 2 front hot-swap 2.5” U.2 per node
High Performance and Balanced Solutions for Accelerated Computing Applications
NVIDIA HGX A100 4-GPU with NVLink, or up to 6 double-width PCIe GPUs
Up to 10 Hot-swap 2.5″ SATA/SAS/NVMe
Highest Density GPU Platforms for Deployments from the Data Center to the Edge
Up to 4 double-width PCIe GPUs
Intel® Xeon®
Up to 16 DIMMs, 4TB
Up to 6 x 2.5″ Hot-swap SAS/SATA, or 2 x 2.5″ Hot-swap NVMe SATA/SAS/NVMe
Flexible Solution for AI/Deep Learning Practitioners and High-end Graphics Professionals
Up to 16 DIMMs, 6TB
Up to 8 hot-swap 2.5” SATA/NVMe
We’re committed to having your back no matter the issue or time of day, starting when we first connect.
Get the answers you need fast with guidance from our support team.
Stay within your budget by paying the lowest, most up-to-date market prices.
Avoid paying hefty shipping fees each time you need a new product.