Hopper Architecture
NVIDIA H100 SXM
NVIDIA H100 SXM5 Tensor Core GPU — Rent GPU servers for AI training, inference, and HPC.
Memory
80 GB
HBM3
FP32
60
TFLOPS
Bandwidth
3350
GB/s
Avg. Price
$1.5
per hour
Hardware · Specifications
Full specs.
ManufacturerNVIDIA
ArchitectureHopper
Release Year2022
VRAM80 GB HBM3
Memory Bandwidth3350 GB/s
FP32 Performance60 TFLOPS
FP16 Performance120 TFLOPS
INT8 Performance2400 TOPS
Tensor Cores16896
CUDA/Stream Processors16896
TDP700W
Form FactorSXM
NVLink SupportYes
Max GPUs per Node8
Compute · Performance
Performance overview.
FP32 Single Precision
60
TFLOPS
FP16 Half Precision
120
TFLOPS
INT8 Integer Ops
2400
TOPS
Workloads · Use Cases
Ideal for.
Deep Learning Training
LLM Fine-tuning
AI Research
HPC
Cost · Pricing
Transparent pricing.
Hourly$1.50/hr
Daily$36.00/day
Monthly$1095.00/mo
Platform · Why Runcrate
Why rent NVIDIA H100 SXM.
Deploy in 60 Seconds
Get instant access to NVIDIA H100 SXM. No setup required, start training immediately.
Pay Per Second
Only pay for what you use. Stop instances anytime. No hidden fees.
Enterprise Ready
99.9% uptime guarantee. 24/7 support. Production-grade infrastructure.
Support · FAQ