PCIe GPU server
Flexible accelerator and network options within the manufacturer support matrix. Suitable configurations depend on card power, slot spacing, airflow and application requirements.
Loading products and specifications…
Loading products and specifications…
Transaction requirements
Direct paying buyers only.
Catalogue at a glance
Select a product line to browse the models in that range. Counts show products, not available stock.
Products & specifications
Illustrative and reference images show product families or models. Request offered-unit photographs, labels and included items before confirming an order.
AI server planning
Select a server and quantity. Add your rack-space and power estimates to the quotation request.
A closer look at enterprise hardware
Explore component handling, system scale and packaging through illustrative scenes. These images show typical product-category settings, not offered inventory; request photographs of the specific unit with your quotation.
Buying for a project?
Keep the model, quantity and installation requirements together.
Find matching catalogue entries, review different versions and bring the selected products into your RFQ.
Check a parts list ↗02 · Plan the connectionsExplore server, switch and storage examples. Check host interfaces, optics and redundancy before choosing components.
Explore storage connections ↗03 · Prepare your requestAdd quantities, condition, testing and destination. Prices and availability are confirmed before an order is accepted.
Open your RFQ ↗Need a quote?
Send the full P/N, quantity, host system and delivery destination.
AI INFRASTRUCTURE / SYSTEMS / SCALE
Discover integrated DGX systems and OEM accelerated servers. Start with the exact platform, compare systems, then define the compute, fabric and deployment requirements together.
208 model entries · 13 manufacturers
Explore AI systems Plan your deployment ↗View warehouse scenes ↗
WAREHOUSE SCENE STUDIES
Explore model-specific handling and packing scenarios with fully supported chassis, low industrial platforms and protective packaging. These are illustrative product-category images, not photographs of available stock. Request current unit photographs with your quotation.
CHOOSE AN ARCHITECTURE
Flexible accelerator and network options within the manufacturer support matrix. Suitable configurations depend on card power, slot spacing, airflow and application requirements.
An integrated multi-GPU baseboard with a specific GPU interconnect. Compare the complete OEM chassis, CPU platform, network layout and cooling arrangement.
Compute trays, switches, power and cooling are integrated at rack level. Plan delivery, floor loading, liquid-cooling interfaces and service access as a complete installation.
COMPUTE → FABRIC → FACILITY
Share model size, inference concurrency or training requirements. Compare accelerator memory, supported precision and interconnect topology using the exact platform documentation.
Check the NICs, switches, optics, storage path and software stack together. Port speed alone does not confirm an end-to-end fabric configuration.
Network equipment ↗Confirm rack height and depth, weight, electrical feed, heat removal, liquid-cooling requirements and service access before planning installation.
Storage platforms ↗DGX identifies integrated NVIDIA systems. HGX is a GPU platform integrated into manufacturer systems. Compare complete server model, GPU configuration, cooling, software and support scope.
No. These groups aid discovery. OEM systems may support several configurations; use their individual documentation and the final bill of materials to establish compatibility.
No. Product reference images show product construction; generated scenes are illustrative. Ask for current photos of the offered unit or batch when requesting a quotation.
ENGINEERING REVIEW / BEFORE THE QUOTATION
Build the enquiry around the complete configuration. Use the review points below to identify the details that need confirmation for your project.
Specify the complete OEM platform and accelerator configuration, including GPU form factor and interconnect arrangement.
Describe training or inference, workload scale, software stack and licensing requirements.
Plan NICs, switching, optics, cables and storage bandwidth with the intended topology.
Confirm site power capacity and the exact system cooling requirements, including liquid connections where applicable.
Record packed dimensions and weight requirements, access restrictions and the site lifting plan.
Agree the configuration inventory, diagnostic workload and environmental conditions for acceptance.
DELIVERY & SUPPORT
Agree the exact system configuration and test scope. Include rack loading, power feeds, cooling connections and receiving equipment in the deployment review.
Confirm the appropriate crate, handling points, packed weight and dimensions for the specified system. Plan shipment documents and lifting arrangements with the receiving site.
Confirm included support, software entitlements, warranty coverage and the acceptance process in writing before ordering.
AI GPU Servers
P/NESC N8-E11V
AI Server
P/NESC-N8-E11
AI Server
P/NESC-NM2N721-E1
AI Server
P/NESC-A8A-E12U
AI Server
P/NESC-NB8-E11
AI Server
P/NESC4000-E10
AI Server
P/NESC4000-E11
AI Server
P/NESC4000A-E10
AI Server
P/NESC4000A-E12
AI Server
P/NESC4000A-E11
AI Server
P/NESC8000-E11
AI Server
P/NESC8000-E11P
AI Server
P/NESC8000-E12
AI Server
P/NESC8000A-E12P
AI Server
P/NESC8000-E12P
AI Server
P/NESC8000A-E12
AI Server
P/NESC8000A-E13
AI Server
P/NESC8000A-E13P
AI Server
P/NESC8000A-E13X
GPU Platform
P/NXA NB3I-E12
AI Server
P/NXA-GB721-E2
AI GPU Servers
P/NPowerEdge XE7740
AI GPU Servers
P/NPowerEdge XE7745