Geekbench ML Score

584
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 21 2024 01:23 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% 379
70.9 IPS
 
Image Classification (F16)
100% 360
67.3 IPS
 
Image Classification (I8)
99% 213
39.9 IPS
 
Image Segmentation (F32)
100% 276
4.61 IPS
 
Image Segmentation (F16)
100% 239
4.00 IPS
 
Image Segmentation (I8)
100% 232
3.87 IPS
 
Pose Estimation (F32)
100% 1557
1.89 IPS
 
Pose Estimation (F16)
100% 6325
7.66 IPS
 
Pose Estimation (I8)
100% 1142
1.38 IPS
 
Object Detection (F32)
100% 375
28.0 IPS
 
Object Detection (F16)
100% 443
33.0 IPS
 
Object Detection (I8)
97% 192
14.3 IPS
 
Face Detection (F32)
100% 766
9.11 IPS
 
Face Detection (F16)
100% 1031
12.3 IPS
 
Face Detection (I8)
99% 427
5.07 IPS
 
Depth Estimation (F32)
100% 1589
12.3 IPS
 
Depth Estimation (F16)
99% 681
5.28 IPS
 
Depth Estimation (I8)
99% 1721
13.3 IPS
 
Style Transfer (F32)
100% 3652
4.80 IPS
 
Style Transfer (F16)
100% 2962
3.90 IPS
 
Style Transfer (I8)
100% 3356
4.42 IPS
 
Image Super-Resolution (F32)
100% 623
22.3 IPS
 
Image Super-Resolution (F16)
100% 1160
41.4 IPS
 
Image Super-Resolution (I8)
100% 1907
68.1 IPS
 
Text Classification (F32)
100% 266
382.8 IPS
 
Text Classification (F16)
100% 148
213.0 IPS
 
Text Classification (I8)
96% 144
207.3 IPS
 
Machine Translation (F32)
100% 138
2.53 IPS
 
Machine Translation (F16)
99% 192
3.53 IPS
 
Machine Translation (I8)
99% 133
2.45 IPS
 

Compare

Set Baseline Geekbench 6 now available