Geekbench ML Score

3164
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 03:14 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.46 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7641
818.7 IPS
 
Image Classification (F16)
100% 7567
810.8 IPS
 
Image Classification (I8)
81% 750
80.3 IPS
 
Image Segmentation (F32)
100% 2344
14.5 IPS
 
Image Segmentation (F16)
100% 2335
14.4 IPS
 
Image Segmentation (I8)
89% 1351
8.34 IPS
 
Pose Estimation (F32)
100% 27907
112.9 IPS
 
Pose Estimation (F16)
100% 27639
111.8 IPS
 
Pose Estimation (I8)
80% 260
1.05 IPS
 
Object Detection (F32)
100% 8693
305.1 IPS
 
Object Detection (F16)
100% 8616
302.4 IPS
 
Object Detection (I8)
52% 1051
36.9 IPS
 
Face Detection (F32)
100% 9694
111.4 IPS
 
Face Detection (F16)
100% 9704
111.5 IPS
 
Face Detection (I8)
75% 1030
11.8 IPS
 
Text Classification (F32)
100% 1316
520.6 IPS
 
Text Classification (F16)
100% 1332
526.8 IPS
 
Machine Translation (F32)
100% 1928
297.1 IPS
 
Machine Translation (F16)
100% 1932
297.7 IPS
 

Compare

Set Baseline