Brand: Dell | Category: Servers
SKU: DELL-PEXE9712 | Part #: PEXE9712 | MPN: PEXE9712
Contact for Pricing — Request a Quote
The Dell PowerEdge XE9712 GPU Server from Dell is enterprise-grade Servers hardware built for data centers. Dell's rack-scale liquid-cooled AI training platform integrating NVIDIA GB300 NVL72 for the most demanding large-scale model development workloads. Available in brand new condition. Dell servers products are trusted by enterprises and data centers worldwide. Available from Omnixon Global. Contact our sales team to request a quote.
| Brand | Dell |
| Category | Servers |
| SKU | DELL-PEXE9712 |
| Part Number | PEXE9712 |
| Condition | New |
| Product Line | PowerEdge XE Series |
| Form Factor | Rack-scale liquid-cooled platform |
| GPU Architecture | NVIDIA Blackwell (GB300 NVL72) |
| GPU Count per Rack | 72 x NVIDIA Blackwell GPUs (GB300) |
| CPU Architecture | NVIDIA Grace CPU (ARM Neoverse V2), 36 Grace CPUs integrated via Grace Blackwell Superchip |
| Superchip Configuration | 36 x NVIDIA GB300 Grace Blackwell Superchips (each comprising 1 Grace CPU + 2 Blackwell GPUs) |
| GPU Memory | Up to 1.44 TB HBM3e aggregate GPU memory across 72 GPUs |
| GPU Interconnect | NVLink 5 with NVLink Switch fabric providing 130 TB/s bisection bandwidth |
| CPU-GPU Interconnect | NVLink-C2C (Chip-to-Chip) per Grace Blackwell Superchip |
| System Memory | High-bandwidth LPDDR5X CPU memory integrated per Grace CPU |
| Cooling Method | Direct liquid cooling (DLC) — rear-door and cold-plate liquid cooling throughout |
| Networking | High-speed front-end and backend network fabrics; supports NVIDIA Quantum-X800 InfiniBand and Spectrum-X800 Ethernet |
| Network Bandwidth | Up to 3200 Gb/s aggregate backend fabric bandwidth per rack |
| Storage Interface | NVMe-based boot and local storage; integration with external all-flash and distributed storage systems |
| Power Input | Three-phase AC high-voltage power delivery optimized for rack-scale deployment |
| Typical Rack Power Envelope | ~120 kW per rack (dependent on workload and configuration) |
| OS Support | Ubuntu Linux, Red Hat Enterprise Linux; optimized for NVIDIA AI Enterprise software stack |
| Management | Dell OpenManage integration; NVIDIA Base Command Manager compatibility; IPMI/BMC |
| AI Software Ecosystem | Dell AI Factory; NVIDIA AI Enterprise; CUDA 12.x; cuDNN; NCCL; Triton Inference Server |
| Launch Availability | 2025 Q2 |
| Target Deployment | Hyperscale data centers, enterprise AI factories, national research computing centers |
The Dell PowerEdge XE9712 GPU Server is built for enterprise data-center workloads — virtualization (VMware, Proxmox, Nutanix), private cloud, database hosting, and AI/ML training. It fits standard EIA-310 server racks and supports redundant PSUs and hot-swap drives common in production environments.
Key specifications for the Dell PowerEdge XE9712 GPU Server: new condition; manufacturer Dell; product line PowerEdge XE Series; form factor Rack-scale liquid-cooled platform; gpu architecture NVIDIA Blackwell (GB300 NVL72); gpu count per rack 72 x NVIDIA Blackwell GPUs (GB300); cpu architecture NVIDIA Grace CPU (ARM Neoverse V2), 36 Grace CPUs integrated via Grace Blackwell Superchip. Manufacturer part number PEXE9712. For the full datasheet with electrical, environmental, and compliance details, contact our pre-sales engineering team.