GPU

• Best for: CSP AIaaS or enterprise Agent Flow AI Inference
• Key Features/Applications: High Performance Computing, VDI/AI/Deep Learning, Media/Video processing, Cloud Gaming, Animation and Modeling, Design & Visualization, 3D Rendering, Diagnostic Imaging
• CPU: Dual Intel® Xeon® 6962P Processor, 72 cores per CPU
• Chassis: 4U of 737mm Depth
• Drive: 1x 960GB M.2 NVMe + 2x 3.84TB NVMe SSD
• RAM: 24x 64GB, Total 1.5TB DDR5-6400 Memory
• GPU: 8x NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPUs
• Network Ports: 2x 10GbE RJ45 + 2x 400G Ethernet/NDR IB + 2x 200G Ethernet/NDR IB Ports
• Power Supply: 4x 3200W Redundant Titanium Level Power Supplies
• Pre-Configured Agent Flow AI Inferencing System (or PaaS CSP AIaaS) with up to 8 GPUs. View Datasheet
• Need more customization? Explore the configurable SYS-422GA-NRT system.

• Best for: SaaS - Agent Flow AI Inference
• Key Features/Applications: AI / Deep Learning, Visualization / Simulation, 3D Rendering Farm, High Performance Computing (HPC), Multimedia/Digital Content creation
• CPU: Dual AMD EPYC™ 9355 Processors, 32 Cores
• Chassis: 5U
• Drive: 1x 960GB M.2 NVMe SSD
• RAM: 24x 64GB DDR5-6400 RDIMM Memory
• GPU: 2x NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPUs
• Network Ports: 2x 10GbE RJ45 LAN Ports
• Power Supply: 6x 2700W Redundant Titanium Level Power Supplies
• Need more customization? Explore the configurable AS -5126GS-TNRT system.

* Estimated lead time is currently 2-3 weeks. Actual delivery schedule will depend on quantity and availability.

• Key Features/Applications: Enterprise AI, Chatbot/RAG, Document Processing, Content Creation, Recommendation, Synthetic Data Generation, Agentic AI, LLM/VLM finetuning/training, HPC, CAD/CAE/CFD, Scientific Research (Modular Dynamics, Weather Forecast, Geological Analysis)
• CPU: Dual Intel® Xeon® 6960P Processor, 72 Cores Per CPU
• Chassis: 4U
• Drive: 1x 960GB M.2 PCIe Gen 4.0 NVMe + 2x 3.8TB U.2 PCIe Gen 4.0 NVMe SSD
• RAM: 16x 64GB DDR5-6400 RDIMM Memory
• GPU: 4x NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPUs
• Network Ports: 2x 10GbE RJ45 LAN Ports (Intel X710-AT2)
• Power Supply: 4x 3200W Redundant Titanium Level Power Supplies
• Pre-Configured Agent Flow AI Inferencing System (PaaS) View Datasheet

* Estimated lead time is currently 2-3 weeks. Actual delivery schedule will depend on quantity and availability.