NVIDIA H100 SXMvsNVIDIA A40
Detailed specifications, performance benchmarks, and pricing comparison to help you choose the right GPU for your AI workloads.
NVIDIA H100 SXM
Hopper · 2022
NVIDIA A40
Ampere · 2020
Specifications · Comparison
Side by side specs.
| Spec | NVIDIA H100 SXM | NVIDIA A40 |
|---|---|---|
| Architecture | Hopper | Ampere |
| VRAM | 80 GB+66.7% | 48 GB |
| Memory Type | HBM3 | GDDR6 |
| Memory Bandwidth | 3350 GB/s+381.3% | 696 GB/s |
| FP32 Performance | 60 TFLOPS+60.4% | 37.4 TFLOPS |
| FP16 Performance | 120 TFLOPS+60.4% | 74.8 TFLOPS |
| INT8 Performance | 2400 TOPS+702.7% | 299 TOPS |
| TDP | 700W | 300W |
| Form Factor | SXM | PCIe |
| Price (avg/hr) | $1.50 | $0.75 |
Performance · Analysis
Performance breakdown.
Compute (FP32)
Raw single-precision floating point throughput
NVIDIA H100 SXM is 60.4% faster
Training (FP16)
Half-precision performance for deep learning training
NVIDIA H100 SXM is 60.4% faster
Inference (INT8)
Integer performance for model inference workloads
NVIDIA H100 SXM is 702.7% faster
Memory Bandwidth
Data transfer rate between memory and compute units
NVIDIA H100 SXM is 381.3% faster
Best Compute
NVIDIA H100 SXM
Most Memory
NVIDIA H100 SXM
Best Training
NVIDIA H100 SXM
Best Value
NVIDIA A40
Pricing · Cost
Cost comparison.
Hourly
Save $0.75 with NVIDIA A40
Daily
Save $18.00 with NVIDIA A40
Monthly
Save $540.00 with NVIDIA A40
Use Cases · Workloads
Best for your workload.
NVIDIA H100 SXM
NVIDIA A40
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.
Related · Comparisons
Compare other GPUs.
FAQ · Questions
Common questions.
Deploy NVIDIA H100 SXM or NVIDIA A40
Get started with GPU cloud computing in minutes. No setup complexity, no long-term commitments.