Geekbench ML Score

64
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 18 2024 12:57 AM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad (6th generation)
Model IDiPad7,5
Motherboard J71bAP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.32 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 256
47.9 IPS
 
Image Classification (F16)
100% 9
1.75 IPS
 
Image Classification (I8)
99% 9
1.65 IPS
 
Image Segmentation (F32)
100% 149
2.50 IPS
 
Image Segmentation (F16)
100% 11
0.18 IPS
 
Image Segmentation (I8)
100% 11
0.18 IPS
 
Pose Estimation (F32)
100% 998
1.21 IPS
 
Pose Estimation (F16)
100% 13
0.02 IPS
 
Pose Estimation (I8)
100% 13
0.02 IPS
 
Object Detection (F32)
100% 236
17.6 IPS
 
Object Detection (F16)
100% 9
0.70 IPS
 
Object Detection (I8)
97% 237
17.7 IPS
 
Face Detection (F32)
100% 460
5.47 IPS
 
Face Detection (F16)
98% 29
0.34 IPS
 
Face Detection (I8)
97% 27
0.32 IPS
 
Depth Estimation (F32)
100% 547
4.24 IPS
 
Depth Estimation (F16)
100% 20
0.15 IPS
 
Depth Estimation (I8)
99% 17
0.13 IPS
 
Style Transfer (F32)
100% 1459
1.92 IPS
 
Style Transfer (F16)
100% 44
0.06 IPS
 
Style Transfer (I8)
100% 43
0.06 IPS
 
Image Super-Resolution (F32)
100% 541
19.3 IPS
 
Image Super-Resolution (F16)
100% 10
0.35 IPS
 
Image Super-Resolution (I8)
100% 9
0.31 IPS
 
Text Classification (F32)
100% 176
253.6 IPS
 
Text Classification (F16)
100% 156
224.8 IPS
 
Text Classification (I8)
96% 157
225.0 IPS
 
Machine Translation (F32)
100% 238
4.38 IPS
 
Machine Translation (F16)
100% 21
0.39 IPS
 
Machine Translation (I8)
99% 256
4.71 IPS
 

Compare

Set Baseline Geekbench 6 now available