Geekbench ML Score

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

Result Information

Upload Date October 24 2021 12:35 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% 643
68.8 IPS
 
Image Classification (F16)
100% 614
65.7 IPS
 
Image Classification (I8)
81% 409
43.9 IPS
 
Image Segmentation (F32)
100% 964
5.96 IPS
 
Image Segmentation (F16)
100% 951
5.88 IPS
 
Image Segmentation (I8)
89% 1396
8.62 IPS
 
Pose Estimation (F32)
100% 358
1.45 IPS
 
Pose Estimation (F16)
100% 354
1.43 IPS
 
Pose Estimation (I8)
80% 441
1.78 IPS
 
Object Detection (F32)
100% 927
32.5 IPS
 
Object Detection (F16)
100% 924
32.4 IPS
 
Object Detection (I8)
52% 704
24.7 IPS
 
Face Detection (F32)
100% 1094
12.6 IPS
 
Face Detection (F16)
100% 1064
12.2 IPS
 
Face Detection (I8)
75% 811
9.31 IPS
 
Text Classification (F32)
100% 2339
924.9 IPS
 
Text Classification (F16)
100% 2328
920.7 IPS
 
Machine Translation (F32)
100% 1683
259.4 IPS
 
Machine Translation (F16)
100% 1680
258.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download