Geekbench ML Score

115
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date July 22 2021 09:48 AM
Views 1

System Information

System Information
Operating System iOS 14.7
Model iPad mini 4
Model IDiPad5,1
Motherboard J96AP
CPU Information
Name Apple A8
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.50 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache1.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 90
9.64 IPS
 
Image Classification (F16)
100% 90
9.63 IPS
 
Image Classification (I8)
81% 148
15.8 IPS
 
Image Segmentation (F32)
100% 147
0.91 IPS
 
Image Segmentation (F16)
100% 147
0.91 IPS
 
Image Segmentation (I8)
89% 273
1.69 IPS
 
Pose Estimation (F32)
100% 37
0.15 IPS
 
Pose Estimation (F16)
100% 37
0.15 IPS
 
Pose Estimation (I8)
80% 51
0.21 IPS
 
Object Detection (F32)
100% 139
4.88 IPS
 
Object Detection (F16)
100% 139
4.87 IPS
 
Object Detection (I8)
52% 209
7.35 IPS
 
Face Detection (F32)
100% 150
1.73 IPS
 
Face Detection (F16)
100% 149
1.71 IPS
 
Face Detection (I8)
75% 201
2.31 IPS
 
Text Classification (F32)
98% 70
27.5 IPS
 
Text Classification (F16)
98% 70
27.8 IPS
 
Machine Translation (F32)
100% 189
29.1 IPS
 
Machine Translation (F16)
100% 188
29.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download