Geekbench ML Score

3454
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 17.5.1
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.48 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.31 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1496
280.0 IPS
 
Image Classification (F16)
100% 1906
356.7 IPS
 
Image Classification (I8)
99% 1886
353.0 IPS
 
Image Segmentation (F32)
100% 801
13.4 IPS
 
Image Segmentation (F16)
100% 801
13.4 IPS
 
Image Segmentation (I8)
100% 794
13.3 IPS
 
Pose Estimation (F32)
100% 5881
7.12 IPS
 
Pose Estimation (F16)
100% 13782
16.7 IPS
 
Pose Estimation (I8)
100% 13862
16.8 IPS
 
Object Detection (F32)
100% 1472
109.9 IPS
 
Object Detection (F16)
100% 2016
150.5 IPS
 
Object Detection (I8)
97% 1482
110.6 IPS
 
Face Detection (F32)
100% 2851
33.9 IPS
 
Face Detection (F16)
97% 4364
51.9 IPS
 
Face Detection (I8)
97% 4357
51.8 IPS
 
Depth Estimation (F32)
100% 5359
41.6 IPS
 
Depth Estimation (F16)
100% 8605
66.7 IPS
 
Depth Estimation (I8)
99% 8607
66.7 IPS
 
Style Transfer (F32)
100% 16987
22.3 IPS
 
Style Transfer (F16)
100% 26521
34.9 IPS
 
Style Transfer (I8)
100% 26531
34.9 IPS
 
Image Super-Resolution (F32)
100% 3738
133.5 IPS
 
Image Super-Resolution (F16)
100% 5007
178.8 IPS
 
Image Super-Resolution (I8)
100% 4857
173.5 IPS
 
Text Classification (F32)
100% 2086
3.00 KIPS
 
Text Classification (F16)
100% 2940
4.23 KIPS
 
Text Classification (I8)
96% 2936
4.22 KIPS
 
Machine Translation (F32)
100% 1274
23.4 IPS
 
Machine Translation (F16)
100% 1539
28.3 IPS
 
Machine Translation (I8)
99% 1267
23.3 IPS
 

Compare

Set Baseline Geekbench 6 now available