Maximum Performance of YOLOv3 model for NVIDIA T4 in TensorRT using trtexec

Can you please give the maximum Performance of YOLOv3 model reported in TensorRT using trtexec??


TensorRT Version :
GPU Type : T4
Nvidia Driver Version : 440+
CUDA Version : 10.2
CUDNN Version :
Operating System + Version : 18.04

Can you please some one will be able to provide any inputs/help regarding the same.