Geekbench ML Score

5273
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 26 2024 12:34 PM
Views 1

System Information

System Information
Operating System iOS 18.0
Model iPad16,3
Model IDiPad16,3
Motherboard J717AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 4.40 GHz
Cluster 13 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.29 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1942
363.3 IPS
 
Image Classification (F16)
100% 3364
629.5 IPS
 
Image Classification (I8)
99% 3340
625.0 IPS
 
Image Segmentation (F32)
100% 1317
22.0 IPS
 
Image Segmentation (F16)
100% 1709
28.5 IPS
 
Image Segmentation (I8)
100% 1703
28.4 IPS
 
Pose Estimation (F32)
100% 9710
11.8 IPS
 
Pose Estimation (F16)
100% 18348
22.2 IPS
 
Pose Estimation (I8)
100% 18315
22.2 IPS
 
Object Detection (F32)
100% 2030
151.6 IPS
 
Object Detection (F16)
100% 3133
233.9 IPS
 
Object Detection (I8)
97% 2034
151.8 IPS
 
Face Detection (F32)
100% 3886
46.2 IPS
 
Face Detection (F16)
97% 7362
87.5 IPS
 
Face Detection (I8)
97% 7346
87.4 IPS
 
Depth Estimation (F32)
100% 8234
63.9 IPS
 
Depth Estimation (F16)
100% 14561
112.9 IPS
 
Depth Estimation (I8)
99% 14591
113.2 IPS
 
Style Transfer (F32)
100% 24510
32.2 IPS
 
Style Transfer (F16)
100% 37022
48.7 IPS
 
Style Transfer (I8)
100% 37041
48.7 IPS
 
Image Super-Resolution (F32)
100% 6019
215.0 IPS
 
Image Super-Resolution (F16)
100% 7070
252.5 IPS
 
Image Super-Resolution (I8)
100% 7054
251.9 IPS
 
Text Classification (F32)
100% 2764
3.97 KIPS
 
Text Classification (F16)
100% 4820
6.93 KIPS
 
Text Classification (I8)
96% 4834
6.95 KIPS
 
Machine Translation (F32)
100% 1665
30.6 IPS
 
Machine Translation (F16)
100% 1973
36.3 IPS
 
Machine Translation (I8)
99% 1660
30.6 IPS
 

Compare

Set Baseline Geekbench 6 now available