NVIDIAAI GPU · PCIe
A10
NVIDIA A10 is a Ampere data-center accelerator with 24 GB GDDR6 and 0.6 TB/s of memory bandwidth.
Specifications
Dense throughput, no sparsity| Architecture | Ampere |
|---|---|
| Form factor | PCIe |
| Process | Samsung 8 nm |
| FP16 / BF16 tensor (dense) | 125 TFLOPS |
| FP8 tensor (dense) | — |
| FP4 tensor (dense) | — |
| Memory | 24 GB GDDR6 |
| Memory bandwidth | 0.6 TB/s |
| Power | 150 W |
| Launch | Apr 2021 |
AI index
Tensor × bandwidth100 × √((125 ÷ 989.4) × (0.6 ÷ 3.35)) = 15.0
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.