Dell PowerEdge XE9712 GPU Server

The Dell PowerEdge XE9712 is a purpose-built rack-scale GPU server platform designed around the NVIDIA GB300 NVL72 architecture, delivering an unprecedented density of Grace Blackwell Superchip compute within a single liquid-cooled rack unit. The system integrates 72 NVIDIA Blackwell GPUs and 36 Grace CPUs through NVLink interconnect fabric, forming a unified high-bandwidth compute domain optimized for trillion-parameter model training and inference. Available exclusively through the Dell AI Factory ecosystem, the XE9712 represents Dell's most capable AI infrastructure offering to date, engineered for hyperscale operators and enterprise AI pioneers building next-generation foundation models.

Ideal for

• Large-scale foundation model pre-training for trillion-parameter language and multimodal models
• Hyperscale AI research clusters requiring maximum NVLink-connected GPU density per rack
• Reinforcement learning from human feedback (RLHF) pipelines at enterprise and cloud scale
• Scientific simulation workloads such as climate modeling, drug discovery, and genomics
• High-throughput AI inference serving for latency-sensitive generative AI applications
• Government and national laboratory AI supercomputing initiatives demanding liquid-cooled high-density infrastructure

Technical specifications

Available from Omnixon Global. Submit an RFQ and our team will confirm configuration and availability for your order.