Technical Specifications

Peak Double Precision Performance

  • 7 TFlops

Peak Single Precision Performance

  • 14 TFlops

Number of accelerators per card

  • 1


  • 5120

Memory size per board

  • 32 GB HBM2

Memory bandwidth for board

  • 900 GB/s

Accelerator applications

  • Deep Learning Training, Memory Capacity-Bound HPC, Compute Bound HPC

Architecture features

  • NVIDIA Tesla V100 32GB doubles the GPU memory to improve performance for AI training, HPC, database, and graphic analytics workloads while reducing costs and complexity.


  • Compatible with HPE ProLiant XL270d Gen10 server


  • For details on HPE Qualified Options Limited Warranty visit: 1-year parts, 1-year labor, and 1-year on-site support coverage. For more warranty information refer to http://h20564.www2.hpe.com/hpsc/wc/public/home
  • *
    Price may vary based on local reseller.