Geekbench ML Score

2697
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 07:33 AM
Views 1

System Information

System Information
Operating System iOS 15.7
Model iPad13,16
Model IDiPad13,16
Motherboard J407AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.45 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6094
652.9 IPS
 
Image Classification (F16)
100% 6073
650.7 IPS
 
Image Classification (I8)
81% 686
73.5 IPS
 
Image Segmentation (F32)
100% 2237
13.8 IPS
 
Image Segmentation (F16)
100% 2225
13.7 IPS
 
Image Segmentation (I8)
89% 1232
7.61 IPS
 
Pose Estimation (F32)
100% 19759
80.0 IPS
 
Pose Estimation (F16)
100% 19118
77.4 IPS
 
Pose Estimation (I8)
80% 236
0.96 IPS
 
Object Detection (F32)
100% 7336
257.4 IPS
 
Object Detection (F16)
100% 7297
256.1 IPS
 
Object Detection (I8)
52% 968
34.0 IPS
 
Face Detection (F32)
100% 7883
90.6 IPS
 
Face Detection (F16)
100% 7895
90.7 IPS
 
Face Detection (I8)
75% 948
10.9 IPS
 
Text Classification (F32)
100% 1049
415.0 IPS
 
Text Classification (F16)
100% 1039
411.1 IPS
 
Machine Translation (F32)
100% 1823
281.0 IPS
 
Machine Translation (F16)
100% 1828
281.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download