Geekbench ML Score

1602
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 05:59 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1431
153.3 IPS
 
Image Classification (F16)
100% 1567
167.9 IPS
 
Image Classification (I8)
81% 638
68.3 IPS
 
Image Segmentation (F32)
100% 4166
25.7 IPS
 
Image Segmentation (F16)
100% 5797
35.8 IPS
 
Image Segmentation (I8)
89% 1101
6.80 IPS
 
Pose Estimation (F32)
100% 1470
5.95 IPS
 
Pose Estimation (F16)
100% 4954
20.0 IPS
 
Pose Estimation (I8)
80% 211
0.86 IPS
 
Object Detection (F32)
100% 1677
58.9 IPS
 
Object Detection (F16)
99% 1685
59.1 IPS
 
Object Detection (I8)
52% 902
31.7 IPS
 
Face Detection (F32)
100% 4245
48.8 IPS
 
Face Detection (F16)
97% 5502
63.2 IPS
 
Face Detection (I8)
75% 851
9.78 IPS
 
Text Classification (F32)
100% 849
335.7 IPS
 
Text Classification (F16)
98% 1075
425.0 IPS
 
Machine Translation (F32)
100% 1694
261.0 IPS
 
Machine Translation (F16)
100% 1705
262.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download