Showing 2050–2060 of 2196 results

The Supermicro AS-4125GS-TNRT1 is a high-performance GPU A+ Server optimized for AI, HPC, and deep learning workloads. Powered by a single AMD EPYC 9004 Genoa CPU, it features a direct-attached backplane supporting up to 24 hot-swap drives, including 2 SATA drives with RAID 1, 8 NVMe drives, and optional expansion for an additional 16 SATA/SAS drives via SAS controller cards. The system supports up to 10 GPUs (Single Root), including NVIDIA H100 and AMD Instinct MI210, enabling exceptional compute acceleration. Dual 10Gb/s Intel Ethernet ports and a dedicated RJ45 IPMI 2.0 port provide secure remote management, KVM access, and virtual media mounting. With 80 PLUS Titanium power supplies and a rackmount rail kit, it ensures scalable, energy-efficient, and reliable performance.

The Supermicro SYS-220TP-HC8TR is a high-density 2U 4-node BigTwin server engineered for mission-critical enterprise workloads and hyper-converged infrastructure (HCI). Each of the four hot-swappable nodes supports dual 3rd Gen Intel Xeon Scalable processors, providing a massive compute footprint within a compact 2U chassis. This architecture is specifically designed for data center environments where rack space and power efficiency are primary constraints.

The Supermicro SYS-621BT-HNC8R is a high-density 2U 4-node BigTwin system engineered for enterprise-grade hyper-converged infrastructure (HCI) and high-performance computing (HPC) workloads. Each of the four hot-pluggable nodes supports dual 4th Gen Intel Xeon Scalable processors, delivering massive core density and compute power within a compact rack footprint. This multi-node architecture is specifically designed to solve space and power efficiency challenges in modern data centers, allowing for granular scaling of compute resources without the overhead of individual chassis management.

The Supermicro SYS-421GE-TNRT3 is a high-density 4U rackmount server engineered for intensive GPU-accelerated workloads. Built on the 4th Gen Intel Xeon Scalable processor architecture (Sapphire Rapids), this system supports up to 8 double-width PCIe 5.0 x16 GPUs, making it a cornerstone for deep learning, molecular modeling, and high-performance computing (HPC) environments. It addresses the critical bottleneck of data throughput by utilizing PCIe 5.0 lanes, ensuring maximum bandwidth between the CPUs and hardware accelerators.

Supermicro AS-4145GH-TNBR is a high-performance GPU A+ Server designed for AI, HPC, and large-scale analytics workloads. It supports quad AMD Instinct MI300A accelerators, delivering massive parallel processing power for deep learning, scientific computing, and data-intensive applications. The server features a direct-attached backplane supporting up to 24 drives, with 8 hot-plug NVMe drives included by default, while SATA and SAS drives are supported via additional components. A dedicated RJ45 IPMI 2.0 port allows secure remote management, KVM access, and virtual media mounting. Engineered for energy-efficient, scalable, and reliable operation, the AS-4145GH-TNBR is ideal for research labs, AI infrastructure, and enterprise HPC deployments.

The Supermicro AS-4124GO-NART+ is a high-performance GPU A+ Server engineered for AI, HPC, and deep learning workloads. It features a direct-attached backplane supporting 6 hot-plug NVMe drives, configurable as 2 NVMe plus 4 SATA drives, with optional SAS expansion supporting up to 6 additional SATA/SAS drives. Four extra NVMe bays on the rear panel provide further storage scalability. The system supports NVIDIA HGX A100 8-GPU with NVLink, each with 8 dedicated network cards for high-speed GPU interconnects. A dedicated RJ45 IPMI 2.0 port enables secure remote management with KVM and virtual media mount.

The Supermicro SYS-424GP-TNAR+ is a high-density 4U rackmount server engineered specifically for large-scale AI training, Large Language Model (LLM) development, and complex High-Performance Computing (HPC) workloads. Built around the NVIDIA HGX H100 8-GPU baseboard, this system leverages high-speed NVLink and NVSwitch interconnects to provide massive GPU-to-GPU bandwidth, which is essential for distributed deep learning tasks and reducing synchronization bottlenecks.

Supermicro GPU server AS-4124GS-TNR+ is with direct-attached backplane supporting up to 24 hot-swap drives, natively supports 2 SATA with RAID 1 option and 4 NVMe drives. With optional SAS controller cards also additional 18 SATA/SAS drives are supported. Supports up to 8 GPUs, also Nvidia A100 and AMD Instinct MI210. Direct connect for maximum performance. On board dual 1Gb/s Intel Ethernet Controller (2x RJ45) and dedicated RJ45 port for IPMI 2.0 remote management with KVM and remote virtual media mount.

The Supermicro SYS-420GP-TNR is a high-performance GPU server engineered for AI, HPC, and deep learning workloads. Featuring a direct-attached backplane with 24 hot-swap drives, it natively supports 8 SATA and 8 NVMe drives, with optional SAS controller cards enabling up to 16 additional SATA/SAS drives. The system accommodates up to 8 GPUs, including NVIDIA A100, using Dual Root Topology for optimized CPU-to-GPU communication and balanced performance in compute-intensive applications. Networking is provided via dual 1Gb/s Intel Ethernet (2x RJ45) and a dedicated RJ45 IPMI 2.0 port for remote management, KVM, and virtual media mounting. With 80 PLUS Titanium power supplies and a rackmount rail kit, it ensures energy-efficient, scalable, and reliable GPU acceleration.

The Supermicro SYS-6028TP-DNCTR is a high-density 2U TwinPro architecture server designed for enterprise-grade virtualization, hyper-converged infrastructure (HCI), and high-availability storage clusters. By housing two independent hot-plug nodes within a single 2U chassis, this system significantly reduces rack space requirements and power consumption without compromising on compute performance. Each node is powered by dual Intel Xeon E5-2600 v4/v3 processors and supports up to 2TB of DDR4 ECC memory across 16 DIMM slots, making it a robust choice for memory-intensive applications and large-scale container orchestration.