Geekbench ML Score

689
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date July 22 2021 10:01 AM
Views 1

System Information

System Information
Operating System iOS 14.6
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 653
70.0 IPS
 
Image Classification (F16)
100% 628
67.3 IPS
 
Image Classification (I8)
81% 235
25.2 IPS
 
Image Segmentation (F32)
100% 930
5.74 IPS
 
Image Segmentation (F16)
100% 881
5.44 IPS
 
Image Segmentation (I8)
89% 1248
7.71 IPS
 
Pose Estimation (F32)
100% 302
1.22 IPS
 
Pose Estimation (F16)
100% 291
1.18 IPS
 
Pose Estimation (I8)
80% 352
1.42 IPS
 
Object Detection (F32)
100% 846
29.7 IPS
 
Object Detection (F16)
100% 847
29.7 IPS
 
Object Detection (I8)
52% 425
14.9 IPS
 
Face Detection (F32)
100% 1053
12.1 IPS
 
Face Detection (F16)
100% 996
11.4 IPS
 
Face Detection (I8)
75% 675
7.75 IPS
 
Text Classification (F32)
100% 664
262.6 IPS
 
Text Classification (F16)
100% 685
270.8 IPS
 
Machine Translation (F32)
100% 1703
262.5 IPS
 
Machine Translation (F16)
100% 1697
261.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download