GPU Comparison

NVIDIA A100 PCIevsNVIDIA H100 SXM

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

NVIDIA

NVIDIA A100 PCIe

Ampere · 2020

VRAM80 GB HBM2e
FP3219.5 TFLOPS
FP1678 TFLOPS
Bandwidth1935 GB/s
TDP300W
Price$0.98/hr
NVIDIA

NVIDIA H100 SXM

Hopper · 2022

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

Specifications · Comparison

Side by side specs.

SpecNVIDIA A100 PCIeNVIDIA H100 SXM
ArchitectureAmpereHopper
VRAM80 GB80 GB
Memory TypeHBM2eHBM3
Memory Bandwidth1935 GB/s3350 GB/s+42.2%
FP32 Performance19.5 TFLOPS60 TFLOPS+67.5%
FP16 Performance78 TFLOPS120 TFLOPS+35%
INT8 Performance624 TOPS2400 TOPS+74%
TDP300W700W
Form FactorPCIeSXM
Price (avg/hr)$0.98$1.50

Performance · Analysis

Performance breakdown.

Compute (FP32)

Raw single-precision floating point throughput

NVIDIA A100 PCIe
19.5TFLOPS
NVIDIA H100 SXM
60TFLOPSWinner

NVIDIA H100 SXM is 67.5% faster

Training (FP16)

Half-precision performance for deep learning training

NVIDIA A100 PCIe
78TFLOPS
NVIDIA H100 SXM
120TFLOPSWinner

NVIDIA H100 SXM is 35% faster

Inference (INT8)

Integer performance for model inference workloads

NVIDIA A100 PCIe
624TOPS
NVIDIA H100 SXM
2400TOPSWinner

NVIDIA H100 SXM is 74% faster

Memory Bandwidth

Data transfer rate between memory and compute units

NVIDIA A100 PCIe
1935GB/s
NVIDIA H100 SXM
3350GB/sWinner

NVIDIA H100 SXM is 42.2% faster

Best Compute

NVIDIA H100 SXM

Most Memory

NVIDIA A100 PCIe

Best Training

NVIDIA H100 SXM

Best Value

NVIDIA A100 PCIe

Pricing · Cost

Cost comparison.

Hourly

NVIDIA A100 PCIe
$0.98/hr
NVIDIA H100 SXM
$1.50/hr

Save $0.52 with NVIDIA A100 PCIe

Daily

NVIDIA A100 PCIe
$23.52/day
NVIDIA H100 SXM
$36.00/day

Save $12.48 with NVIDIA A100 PCIe

Monthly

NVIDIA A100 PCIe
$705.60/mo
NVIDIA H100 SXM
$1080.00/mo

Save $374.40 with NVIDIA A100 PCIe

Use Cases · Workloads

Best for your workload.

NVIDIA

NVIDIA A100 PCIe

ML Training
AI Inference
Edge AI
NVIDIA

NVIDIA H100 SXM

Deep Learning Training
LLM Fine-tuning
AI Research
HPC

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 A100 PCIe or NVIDIA H100 SXM

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