Geekbench ML Score

880
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 10:23 AM
Views 2

System Information

System Information
Operating System iOS 14.8
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% 617
66.1 IPS
 
Image Classification (F16)
100% 596
63.8 IPS
 
Image Classification (I8)
81% 439
47.0 IPS
 
Image Segmentation (F32)
100% 982
6.07 IPS
 
Image Segmentation (F16)
100% 942
5.82 IPS
 
Image Segmentation (I8)
89% 1380
8.52 IPS
 
Pose Estimation (F32)
100% 351
1.42 IPS
 
Pose Estimation (F16)
100% 349
1.41 IPS
 
Pose Estimation (I8)
80% 430
1.74 IPS
 
Object Detection (F32)
100% 888
31.2 IPS
 
Object Detection (F16)
100% 885
31.1 IPS
 
Object Detection (I8)
52% 750
26.3 IPS
 
Face Detection (F32)
100% 1064
12.2 IPS
 
Face Detection (F16)
100% 1039
11.9 IPS
 
Face Detection (I8)
75% 816
9.37 IPS
 
Text Classification (F32)
100% 2348
928.5 IPS
 
Text Classification (F16)
100% 2345
927.4 IPS
 
Machine Translation (F32)
100% 1680
258.9 IPS
 
Machine Translation (F16)
100% 1675
258.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download