Live
AI hardware

NVIDIA A10G

FP16 throughput
3.1×10¹³ FLOP/s
Memory
22.4 GB
TDP
150 W

NVIDIA A10G is an AI accelerator designed by NVIDIA (GPU), released in April 2021. It is built on a 8 nm process at Samsung, packing 28.3B transistors.

It carries 22.4 GB of memory at 559 GB/s of bandwidth. Its thermal design power is 150 W.

Full record
Manufacturer
NVIDIA
Type
GPU
Release date
Apr 12, 2021
FP32
3.1×10¹³ FLOP/s
FP64
9.8×10¹¹ FLOP/s
Memory
22.4 GB
Memory bandwidth
559 GB
TDP
150 W
Process node
8 nm
Transistors (millions)
28,300
Die size (mm2)
628
Foundry
Samsung
Tensor cores
288
More from NVIDIA
SourceEpoch AI, 'Machine Learning Hardware'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/machine-learning-hardware. Licensed under CC BY 4.0.
← All ai hardware