DatacenterNone available
Rent an H100 SXM
NVIDIA H100 SXM
Industry-leading GPU for AI training with 80GB HBM3 and NVLink support.
Specifications
VRAM80 GB
Memory TypeHBM3
Bandwidth3350 GB/s
CUDA Cores16,896
Tensor Cores528
FP32 Performance67 TFLOPS
FP16 Performance134 TFLOPS
TDP700 W
ArchitectureHopper
GPU ChipGH100
Best for
LLM TrainingLarge Model InferenceHPC
Price per hour
$2.40
Cost estimate
per hour$2.40
per day$57.60
per week$403.20
per month$1728.00
Need H100 servers for months rather than hours? Reserved H100 capacity from data centers.