Geekbench ML Score

864
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 09:39 AM
Views 1

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% 615
65.9 IPS
 
Image Classification (F16)
100% 587
62.9 IPS
 
Image Classification (I8)
81% 437
46.8 IPS
 
Image Segmentation (F32)
100% 931
5.75 IPS
 
Image Segmentation (F16)
100% 890
5.50 IPS
 
Image Segmentation (I8)
89% 1377
8.51 IPS
 
Pose Estimation (F32)
100% 344
1.39 IPS
 
Pose Estimation (F16)
100% 329
1.33 IPS
 
Pose Estimation (I8)
80% 425
1.72 IPS
 
Object Detection (F32)
100% 853
29.9 IPS
 
Object Detection (F16)
100% 854
30.0 IPS
 
Object Detection (I8)
52% 748
26.3 IPS
 
Face Detection (F32)
100% 1025
11.8 IPS
 
Face Detection (F16)
100% 998
11.5 IPS
 
Face Detection (I8)
75% 810
9.30 IPS
 
Text Classification (F32)
100% 2419
956.6 IPS
 
Text Classification (F16)
100% 2351
929.9 IPS
 
Machine Translation (F32)
100% 1691
260.7 IPS
 
Machine Translation (F16)
100% 1681
259.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download