Comprehensive comparison for AI, machine learning, and high-performance computing workloads.
Ampere Architecture
Ampere Architecture
| Specification | NVIDIA A100 SXM | NVIDIA A100 PCIe |
|---|---|---|
| Architecture | Ampere | Ampere |
| Release Year | 2020 | 2020 |
| VRAM | 80 GB | 80 GB |
| Memory Type | HBM2e | HBM2e |
| Memory Bandwidth | 2039 GB/s+5.4% | 1935 GB/s |
| FP32 Performance | 19.5 TFLOPS | 19.5 TFLOPS |
| FP16 Performance | 78 TFLOPS | 78 TFLOPS |
| INT8 Performance | 624 TOPS | 624 TOPS |
| Tensor Cores | 6912 | 6912 |
| CUDA Cores | 6912 | 6912 |
| TDP | 400W | 300W |
| Form Factor | SXM | PCIe |
| NVLink Support | Yes | No |
| Avg. Price/Hour | $1.05+7.1% | $0.98 |
Single-precision floating-point performance for general compute workloads
Half-precision performance optimized for deep learning training
Integer performance for efficient model inference and deployment
Data transfer speed between GPU and memory
NVIDIA A100 SXM is 5.4% faster
NVIDIA A100 PCIe
NVIDIA A100 PCIe
NVIDIA A100 PCIe
NVIDIA A100 PCIe
Enterprise-grade infrastructure
Get a custom quote in 24 hours for reserved GPU clusters with high-speed interconnect, any region, any GPU model, and any number of GPUs you need.
Any GPU
Choose your hardware
Any Quantity
Scale as needed
Any Region
Global availability
Interconnect
High-speed networking
Go from comparison to running workload in under 60 seconds. No complex setup required.
Only pay for what you use. Stop instances anytime. No hidden fees or long-term commitments.
Enterprise-grade infrastructure with 99.9% uptime. Trusted by AI teams worldwide.
Explore more GPU comparisons to find the perfect match for your workload