GPU Comparison

NVIDIA H100 SXMvsNVIDIA H100 PCIe

Detailed specifications, performance benchmarks, and pricing comparison to help you choose the right GPU for your AI workloads.

NVIDIA

NVIDIA H100 SXM

Hopper · 2022

Faster
VRAM80 GB HBM3
FP3260 TFLOPS
FP16120 TFLOPS
Bandwidth3350 GB/s
TDP700W
Price$1.50/hr
NVIDIA

NVIDIA H100 PCIe

Hopper · 2022

VRAM80 GB HBM3
FP3251 TFLOPS
FP16102 TFLOPS
Bandwidth2000 GB/s
TDP350W
Price$1.40/hr

Specifications · Comparison

Side by side specs.

SpecNVIDIA H100 SXMNVIDIA H100 PCIe
ArchitectureHopperHopper
VRAM80 GB80 GB
Memory TypeHBM3HBM3
Memory Bandwidth3350 GB/s+67.5%2000 GB/s
FP32 Performance60 TFLOPS+17.6%51 TFLOPS
FP16 Performance120 TFLOPS+17.6%102 TFLOPS
INT8 Performance2400 TOPS+17.6%2040 TOPS
TDP700W350W
Form FactorSXMPCIe
Price (avg/hr)$1.50$1.40

Performance · Analysis

Performance breakdown.

Compute (FP32)

Raw single-precision floating point throughput

NVIDIA H100 SXM
60TFLOPSWinner
NVIDIA H100 PCIe
51TFLOPS

NVIDIA H100 SXM is 17.6% faster

Training (FP16)

Half-precision performance for deep learning training

NVIDIA H100 SXM
120TFLOPSWinner
NVIDIA H100 PCIe
102TFLOPS

NVIDIA H100 SXM is 17.6% faster

Inference (INT8)

Integer performance for model inference workloads

NVIDIA H100 SXM
2400TOPSWinner
NVIDIA H100 PCIe
2040TOPS

NVIDIA H100 SXM is 17.6% faster

Memory Bandwidth

Data transfer rate between memory and compute units

NVIDIA H100 SXM
3350GB/sWinner
NVIDIA H100 PCIe
2000GB/s

NVIDIA H100 SXM is 67.5% faster

Best Compute

NVIDIA H100 SXM

Most Memory

NVIDIA H100 SXM

Best Training

NVIDIA H100 SXM

Best Value

NVIDIA H100 PCIe

Pricing · Cost

Cost comparison.

Hourly

NVIDIA H100 SXM
$1.50/hr
NVIDIA H100 PCIe
$1.40/hr

Save $0.10 with NVIDIA H100 PCIe

Daily

NVIDIA H100 SXM
$36.00/day
NVIDIA H100 PCIe
$33.60/day

Save $2.40 with NVIDIA H100 PCIe

Monthly

NVIDIA H100 SXM
$1080.00/mo
NVIDIA H100 PCIe
$1008.00/mo

Save $72.00 with NVIDIA H100 PCIe

Use Cases · Workloads

Best for your workload.

NVIDIA

NVIDIA H100 SXM

Deep Learning Training
LLM Fine-tuning
AI Research
HPC
NVIDIA

NVIDIA H100 PCIe

Deep Learning Training
AI Inference
Data Analytics

Platform · Benefits

Why Runcrate.

Instant Deployment

Get your GPU instance running in minutes with pre-configured AI environments. No setup complexity.

Pay Per Hour

Only pay for the compute you actually use. Prepaid credits with transparent, per-hour billing.

Reliable Infrastructure

Enterprise-grade reliability with automatic failover and data persistence across sessions.

FAQ · Questions

Common questions.

Start Building Today

Deploy NVIDIA H100 SXM or NVIDIA H100 PCIe

Get started with GPU cloud computing in minutes. No setup complexity, no long-term commitments.

No credit card required
Pay-per-hour billing
Cancel anytime