Geekbench ML Score

571
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date December 06 2024 09:43 PM
Views 2

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (9.7-inch)
Model IDiPad6,4
Motherboard J128AP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 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 1.92 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 247
46.3 IPS
 
Image Classification (F16)
100% 203
38.0 IPS
 
Image Classification (I8)
99% 204
38.1 IPS
 
Image Segmentation (F32)
100% 173
2.90 IPS
 
Image Segmentation (F16)
100% 164
2.74 IPS
 
Image Segmentation (I8)
100% 175
2.93 IPS
 
Pose Estimation (F32)
100% 2067
2.50 IPS
 
Pose Estimation (F16)
100% 2050
2.48 IPS
 
Pose Estimation (I8)
100% 2022
2.45 IPS
 
Object Detection (F32)
100% 376
28.1 IPS
 
Object Detection (F16)
100% 400
29.9 IPS
 
Object Detection (I8)
97% 398
29.7 IPS
 
Face Detection (F32)
100% 1234
14.7 IPS
 
Face Detection (F16)
100% 1167
13.9 IPS
 
Face Detection (I8)
99% 1157
13.8 IPS
 
Depth Estimation (F32)
100% 2144
16.6 IPS
 
Depth Estimation (F16)
100% 2090
16.2 IPS
 
Depth Estimation (I8)
99% 2182
16.9 IPS
 
Style Transfer (F32)
100% 4788
6.30 IPS
 
Style Transfer (F16)
100% 4760
6.26 IPS
 
Style Transfer (I8)
100% 5082
6.68 IPS
 
Image Super-Resolution (F32)
100% 1139
40.7 IPS
 
Image Super-Resolution (F16)
100% 1066
38.1 IPS
 
Image Super-Resolution (I8)
100% 1145
40.9 IPS
 
Text Classification (F32)
100% 52
74.3 IPS
 
Text Classification (F16)
100% 96
138.1 IPS
 
Text Classification (I8)
96% 97
139.1 IPS
 
Machine Translation (F32)
100% 129
2.38 IPS
 
Machine Translation (F16)
100% 102
1.87 IPS
 
Machine Translation (I8)
99% 117
2.15 IPS
 

Compare

Set Baseline Geekbench 6 now available