En vivo
AI hardware

NVIDIA Tesla P4

FP16 throughput
8.9×10¹⁰ FLOP/s
Memory
7.5 GB
TDP
75 W

NVIDIA Tesla P4 is an AI accelerator designed by NVIDIA (GPU), released in September 2016. It is built on a 16 nm process at TSMC, packing 7.2B transistors.

It carries 7.5 GB of memory at 179 GB/s of bandwidth. Its thermal design power is 75 W.

Full record
Manufacturer
NVIDIA
Type
GPU
Release date
Sep 13, 2016
FP32
5.7×10¹² FLOP/s
FP64
1.8×10¹¹ FLOP/s
INT8
2.2×10¹³ OP/s
Memory
7.5 GB
Memory bandwidth
179 GB
TDP
75 W
Process node
16 nm
Transistors (millions)
7,200
Die size (mm2)
314
Foundry
TSMC
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