NVIDIA H100 SXM 8-GPU

Flagship Hopper GPU for transformer training and distributed inference. Battle-tested for the widest range of AI workloads.

Hopper flagship FP8 NVLink switch
Starting at
$10,000 /month
USD · Monthly reservation · Discounts available for annual terms
Request a Quote Email Sales

Specifications

GPU H100 80GB SXM5 × 8
CPU Intel Xeon 8468
Memory 2048 GB DDR5-4800 (32 × 64 GB)
Disk 4 × 960 GB SSD + 4 × 3.84 TB NVMe
Network 9 × 400GE IB + 10G RJ45
Power 6 × 3000 W

Deployment

  • Bare-metal or fully managed
  • Provisioning in 72 hours
  • 8 US data center locations
  • 24/7 on-shore NOC