Geekbench ML Score

759
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 21 2024 01:09 PM
Views 1

System Information

System Information
Operating System iOS 17.2
Model iPad Air (5th generation)
Model IDiPad13,16
Motherboard J407AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 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 7.47 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 311
58.1 IPS
 
Image Classification (F16)
100% 537
100.5 IPS
 
Image Classification (I8)
99% 400
74.8 IPS
 
Image Segmentation (F32)
100% 294
4.92 IPS
 
Image Segmentation (F16)
100% 77
1.29 IPS
 
Image Segmentation (I8)
100% 150
2.51 IPS
 
Pose Estimation (F32)
100% 743
0.90 IPS
 
Pose Estimation (F16)
100% 2919
3.53 IPS
 
Pose Estimation (I8)
100% 1907
2.31 IPS
 
Object Detection (F32)
100% 155
11.5 IPS
 
Object Detection (F16)
100% 133
9.92 IPS
 
Object Detection (I8)
97% 192
14.3 IPS
 
Face Detection (F32)
100% 386
4.59 IPS
 
Face Detection (F16)
100% 776
9.23 IPS
 
Face Detection (I8)
99% 835
9.93 IPS
 
Depth Estimation (F32)
100% 3682
28.6 IPS
 
Depth Estimation (F16)
99% 2337
18.1 IPS
 
Depth Estimation (I8)
99% 3087
23.9 IPS
 
Style Transfer (F32)
100% 4735
6.23 IPS
 
Style Transfer (F16)
100% 7167
9.43 IPS
 
Style Transfer (I8)
100% 6852
9.01 IPS
 
Image Super-Resolution (F32)
100% 1830
65.3 IPS
 
Image Super-Resolution (F16)
100% 1369
48.9 IPS
 
Image Super-Resolution (I8)
100% 1842
65.8 IPS
 
Text Classification (F32)
100% 1173
1.69 KIPS
 
Text Classification (F16)
100% 566
813.1 IPS
 
Text Classification (I8)
96% 494
709.4 IPS
 
Machine Translation (F32)
100% 390
7.17 IPS
 
Machine Translation (F16)
99% 426
7.84 IPS
 
Machine Translation (I8)
99% 183
3.37 IPS
 

Compare

Set Baseline Geekbench 6 now available