Geekbench ML Score

496
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date November 05 2024 04:42 PM
Views 2

System Information

System Information
Operating System iOS 16.7.8
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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 277
51.8 IPS
 
Image Classification (F16)
100% 246
46.0 IPS
 
Image Classification (I8)
99% 248
46.4 IPS
 
Image Segmentation (F32)
100% 141
2.36 IPS
 
Image Segmentation (F16)
100% 142
2.37 IPS
 
Image Segmentation (I8)
100% 152
2.53 IPS
 
Pose Estimation (F32)
100% 1879
2.27 IPS
 
Pose Estimation (F16)
100% 1880
2.28 IPS
 
Pose Estimation (I8)
100% 1910
2.31 IPS
 
Object Detection (F32)
100% 321
24.0 IPS
 
Object Detection (F16)
100% 306
22.8 IPS
 
Object Detection (I8)
97% 297
22.2 IPS
 
Face Detection (F32)
100% 1016
12.1 IPS
 
Face Detection (F16)
100% 1027
12.2 IPS
 
Face Detection (I8)
99% 905
10.8 IPS
 
Depth Estimation (F32)
100% 2233
17.3 IPS
 
Depth Estimation (F16)
100% 2081
16.1 IPS
 
Depth Estimation (I8)
99% 1972
15.3 IPS
 
Style Transfer (F32)
100% 4376
5.76 IPS
 
Style Transfer (F16)
100% 4171
5.49 IPS
 
Style Transfer (I8)
100% 4596
6.05 IPS
 
Image Super-Resolution (F32)
100% 935
33.4 IPS
 
Image Super-Resolution (F16)
100% 1008
36.0 IPS
 
Image Super-Resolution (I8)
100% 938
33.5 IPS
 
Text Classification (F32)
100% 54
77.6 IPS
 
Text Classification (F16)
100% 59
84.8 IPS
 
Text Classification (I8)
96% 59
84.8 IPS
 
Machine Translation (F32)
100% 84
1.54 IPS
 
Machine Translation (F16)
100% 80
1.47 IPS
 
Machine Translation (I8)
99% 91
1.68 IPS
 

Compare

Set Baseline Geekbench 6 now available