The Dell AI Factory With NVIDIA Advances Supercomputing-Class Infrastructure Powering the Next Generation of HPC and AI
Dell, Monday, June 22nd, 2026
Dell unveiled the PowerEdge XE8812 with NVIDIA Vera Rubin NVL4, delivering up to 144 GPUs per rack for HPC and AI.
Dell Technologies announced the PowerEdge XE8812, a new addition to the Dell AI Factory with NVIDIA built for the most demanding HPC and AI workloads.
The fanless, direct liquid-cooled system uses NVIDIA Vera Rubin NVL4 architecture, offers 50% more memory per socket and GPU than the prior generation, and delivers up to 144 GPUs per rack, letting organizations run larger models without data staging.
Dell cited deployment momentum at sites including the US DOE's NERSC, France's InstaDeep, the UK's Wellcome Sanger Institute, and Australia's Monash University. The server becomes globally available in early 2027.