Geekbench ML Score

808
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 07:30 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
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 3.58 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 622
66.7 IPS
 
Image Classification (F16)
100% 568
60.9 IPS
 
Image Classification (I8)
81% 406
43.5 IPS
 
Image Segmentation (F32)
100% 894
5.52 IPS
 
Image Segmentation (F16)
100% 830
5.13 IPS
 
Image Segmentation (I8)
89% 1333
8.23 IPS
 
Pose Estimation (F32)
100% 321
1.30 IPS
 
Pose Estimation (F16)
100% 313
1.27 IPS
 
Pose Estimation (I8)
80% 401
1.62 IPS
 
Object Detection (F32)
100% 800
28.1 IPS
 
Object Detection (F16)
100% 797
28.0 IPS
 
Object Detection (I8)
52% 728
25.6 IPS
 
Face Detection (F32)
100% 945
10.9 IPS
 
Face Detection (F16)
100% 911
10.5 IPS
 
Face Detection (I8)
75% 878
10.1 IPS
 
Text Classification (F32)
100% 1907
754.2 IPS
 
Text Classification (F16)
100% 1615
638.7 IPS
 
Machine Translation (F32)
100% 1690
260.4 IPS
 
Machine Translation (F16)
100% 1695
261.2 IPS
 

Compare

Set Baseline