Geekbench ML Score

1433
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 03:09 PM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad (8th generation)
Model IDiPad11,6
Motherboard J171aAP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.88 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4175
447.4 IPS
 
Image Classification (F16)
100% 4142
443.8 IPS
 
Image Classification (I8)
81% 401
43.0 IPS
 
Image Segmentation (F32)
100% 1360
8.40 IPS
 
Image Segmentation (F16)
100% 1362
8.41 IPS
 
Image Segmentation (I8)
89% 731
4.52 IPS
 
Pose Estimation (F32)
100% 7085
28.7 IPS
 
Pose Estimation (F16)
100% 7142
28.9 IPS
 
Pose Estimation (I8)
80% 140
0.57 IPS
 
Object Detection (F32)
94% 4244
148.9 IPS
 
Object Detection (F16)
94% 4214
147.9 IPS
 
Object Detection (I8)
52% 567
19.9 IPS
 
Face Detection (F32)
67% 4018
46.2 IPS
 
Face Detection (F16)
67% 4022
46.2 IPS
 
Face Detection (I8)
75% 549
6.30 IPS
 
Text Classification (F32)
100% 398
157.5 IPS
 
Text Classification (F16)
100% 404
159.6 IPS
 
Machine Translation (F32)
100% 988
152.2 IPS
 
Machine Translation (F16)
100% 989
152.4 IPS
 

Compare

Set Baseline