Geekbench ML Score

886
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:31 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 632
67.8 IPS
 
Image Classification (F16)
100% 632
67.7 IPS
 
Image Classification (I8)
81% 419
44.9 IPS
 
Image Segmentation (F32)
100% 965
5.96 IPS
 
Image Segmentation (F16)
100% 942
5.82 IPS
 
Image Segmentation (I8)
89% 1410
8.71 IPS
 
Pose Estimation (F32)
100% 360
1.46 IPS
 
Pose Estimation (F16)
100% 354
1.43 IPS
 
Pose Estimation (I8)
80% 436
1.77 IPS
 
Object Detection (F32)
100% 885
31.1 IPS
 
Object Detection (F16)
100% 873
30.6 IPS
 
Object Detection (I8)
52% 727
25.5 IPS
 
Face Detection (F32)
100% 1080
12.4 IPS
 
Face Detection (F16)
100% 1053
12.1 IPS
 
Face Detection (I8)
75% 813
9.34 IPS
 
Text Classification (F32)
100% 2418
956.2 IPS
 
Text Classification (F16)
100% 2355
931.3 IPS
 
Machine Translation (F32)
100% 1692
260.8 IPS
 
Machine Translation (F16)
100% 1685
259.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download