AI and Deep Learning

• Key Features/Applications: Virtualization, Software-defined Storage, AI Inference and Machine Learning, Cloud Computing, Enterprise Server
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 1U
• Drive: Up to 8x 2.5" Hot-Swap NVMe/SATA/SAS Drive Bays. Supports up to 12x 2.5" Hot-Swap NVMe/SATA/SAS Drive Bays (Optional)
• RAM: Up to 8TB of DDR5 ECC RDIMM in 32 DIMM Slots
• GPU: Up to 1 Double-Width or 3 Single-Width GPUs
• Network Ports: Flexible Networking Options

• Key Features/Applications: Virtualization, Software-defined Storage, AI Inference and Machine Learning, Cloud Computing, Enterprise Server
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 2U
• Drive: Up to 8x 2.5" Hot-Swap NVMe/SATA/SAS Drive Bays. Supports up to 16x 2.5" Hot-Swap NVMe/SATA/SAS Drive Bays (Optional)
• RAM: Up to 8TB of DDR5 ECC DRAM in 32 DIMM Slots
• GPU: Up to 4 Double-Width GPUs
• Network Ports: Flexible Networking Options

• Key Features/Applications: High Performance Computing (HPC), VDI, AI/Deep Learning Training, Media/Video Streaming, Cloud Gaming, Animation and Modeling, Design & Visualization, 3D Rendering, Diagnostic Imaging, AI Training
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: Full-Tower/5U Rackmount
• Drive: Up to 8x 3.5" Front Hot-Swap NVMe/SATA/SAS Drive Bays
• RAM: Up to 4TB of DDR5 ECC RDIMM in 16 DIMM Slots
• GPU: Up to 4 Double-Width or Single-Width GPUs
• Network Ports: 2x 10GbE RJ45 LAN Ports
• Power Supply: 2x 2000W Redundant (1 + 1) Titanium Level Power Supplies

• Key Features/Applications: High Performance Computing, VDI, AI/Deep Learning Training, Media/Video Streaming, Cloud Gaming, Animation and Modeling, Design & Visualization, 3D Rendering, Diagnostic Imaging
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 4U
• Drive: Up to 24x 2.5" Front Hot-Swap NVMe/SAS/SATA Drive Bays
• RAM: Up to 8TB of DDR5 ECC RDIMM in 32 DIMM Slots
• GPU: Up to 10 GPUs
• Network Ports: 2x 10GbE RJ45 LAN Ports
• Power Supply: 4x 2700W Redundant (2 + 2) Titanium Level Power Supplies

• Key Features/Applications: High Performance Computing, AI/Deep Learning Training, Large Language Model (LLM) Natural Language Processing
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 2U
• Drive: Up to 8x E1.S Front Hot-Swap NVMe Drive Bays
• RAM: Up to 8TB of DDR5 ECC RDIMM in 32 DIMM Slots
• GPU: Up to 4 GPUs
• Network Ports: 1x 1GbE RJ45 LAN Ports
• Power Supply: 3x 2000W Redundant Titanium Level Power Supplies

* Estimated lead time is currently 8-10 weeks. Actual delivery schedule will depend on quantity and availability.

• Key Features/Applications: High-Performance File System, Diskless HPC Clusters, Scale Out All-Flash NVMe Storage, Big Data Analytics and AI
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 2U / 2 Nodes
• Drive: Up to 12x 2.5" Hot-Swap NVMe/SATA Drive Bays Per Node (2x PCIe 5.0 NVMe/SATA and 10x PCIe 4.0 NVMe/SATA) + 2x M.2 NVMe
• RAM: Up to 4TB of DDR5 ECC RDIMM in 16 DIMM Slots Per Node
• Cooling: Up to 4 Cooling 16.5K RPM Fans Per 2U Enclosure, Shared Cooling Design Liquid Cooling Support
• Network Ports: Network Connectivity via AIOM (OCP 3.0 Compliant)
• Power Supply: 2x 2200W (1 + 1) Redundant Titanium Level Power Supplies, Shared Power Design

* Complete systems only with all 2 nodes populated.

• Key Features/Applications: High Performance Computing, VDI, AI/Deep Learning Training, Media/Video Streaming, Cloud Gaming, Animation and Modeling, Design & Visualization, 3D Rendering, Diagnostic Imaging
• CPU: Dual 4th Gen Intel® Xeon® Scalable Processors, up to 60 Cores
• Chassis: 5U
• Drive: Up to 24x 2.5" Hot-Swap NVMe/SATA/SAS Drive Bays
• RAM: Up to 8TB of DDR5 ECC DRAM in 32 DIMM Slots
• GPU: Up to 10 GPUs
• Power Supply: 4x 2700W (2+2) Redundant Titanium Level Power Supplies
• Supports NVIDIA H200 NVL or RTX PRO™ 6000 Blackwell Server Edition PCIe 5.0 Graphics Cards

* Estimated lead time is currently 8-10 weeks. Actual delivery schedule will depend on quantity and availability.

• Key Features/Applications: Virtualization, Software-defined Storage, AI Inference and Machine Learning, Cloud Computing, Enterprise Server
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 2U
• Drive: Up to 24x 2.5" Front Hot-Swap NVMe/SAS/SATA Drive Bays (Optional)
• RAM: Up to 8TB of DDR5 ECC RDIMM in 32 DIMM Slots
• GPU: Up to 4 GPUs
• Network Ports: Flexible Networking Options with up to 2 AIOM Networking Slots (OCP NIC 3.0 compatible)
• Power Supply: 2x 1600W Redundant Titanium Level Power Supplies

• Key Features/Applications: High Performance Computing, Conversational AI, AI/Deep Learning Training, Business Intelligence & Analytics, Industrial Automation
• CPU: Dual 5th Gen Intel® Xeon® Platinum 8570 Processor, 56 Cores
• Chassis: 10U
• Drive: 8x 3.8TB U.3 NVMe SSD + 2x 1.92TB M.2 NVMe SSD
• RAM: 32x 96GB DDR5-5600 ECC RDIMM Memory
• GPU: 8x NVIDIA HGX™ B200 GPUs
• DPU: 1x NVIDIA BlueField®-3 DPU 200Gb/s
• Network Ports: 8x 400GbE NDR/ETH OSFP + 2x 10GbE RJ45 LAN Ports
• Power Supply: 6x 5250W Redundant (3 + 3) Titanium Level Power Supplies
• Pre-Configured NVIDIA HGX™ B200 8-GPU System

* Estimated lead time is currently 8-10 weeks. Actual delivery schedule will depend on quantity and availability.

• Key Features/Applications: High Performance Computing, AI/Deep Learning Training, Industrial Automation, Retail, Healthcare, Conversational AI, Business Intelligence & Analytics, Drug Discovery, Climate and Weather Modeling, Finance & Economics
• CPU: Dual 5th/4th Gen Intel® Xeon® Scalable Processors, up to 64 Cores
• Chassis: 8U
• Drive: Up to 19x 2.5" Front Hot-Swap NVMe/SATA Drive Bays + 2x M.2 NVMe Slots
• RAM: Up to 8TB of DDR5 ECC RDIMM in 32 DIMM Slots
• GPU: Up to 8 Double-Wide GPUs
• Network Ports: Flexible Networking Options
• Power Supply: 6x 3000W Redundant (3 + 3) Titanium Level Power Supplies
• NVIDIA Certified System. Supports NVIDIA HGX™ H200 8-GPU
• Success Story: Building Massive AI Cloud Scalable Infrastructure for Advanced AI Training

* Estimated lead time is currently 8-10 weeks. Actual delivery schedule will depend on quantity and availability.