NVIDIA Quadro RTX 8000

FP16 throughput

3.3×10¹³ FLOP/s

Memory

44.7 GB

TDP

260 W

NVIDIA Quadro RTX 8000 is an AI accelerator designed by NVIDIA (GPU), released in August 2018. It is built on a 12 nm process at TSMC, packing 18.6B transistors.

It carries 44.7 GB of memory at 626 GB/s of bandwidth. Its thermal design power is 260 W.

Full record

Manufacturer: NVIDIA
Type: GPU
Release date: Aug 13, 2018
FP32: 1.6×10¹³ FLOP/s
FP64: 5.1×10¹¹ FLOP/s
Memory: 44.7 GB
Memory bandwidth: 626 GB
TDP: 260 W
Process node: 12 nm
Transistors (millions): 18,600
Die size (mm2): 754
Foundry: TSMC
Tensor cores: 576