NVIDIAAI GPU · PCIe
A100 PCIe 80GB
NVIDIA A100 PCIe 80GB is a Ampere data-center accelerator with 80 GB HBM2e and 1.935 TB/s of memory bandwidth.
Specifications
Dense throughput, no sparsity| Architecture | Ampere |
|---|---|
| Form factor | PCIe |
| Process | TSMC 7 nm |
| FP16 / BF16 tensor (dense) | 312 TFLOPS |
| FP8 tensor (dense) | — |
| FP4 tensor (dense) | — |
| Memory | 80 GB HBM2e |
| Memory bandwidth | 1.935 TB/s |
| Power | 300 W |
| Launch | Jun 2021 |
AI index
Tensor × bandwidth100 × √((312 ÷ 989.4) × (1.935 ÷ 3.35)) = 42.7
The AI index is the geometric mean of dense 16-bit tensor throughput and memory bandwidth, each relative to the H100 SXM. It is a spec-sheet comparison, not a measured benchmark.