Geekbench ML Score

870
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 11 2021 03:32 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% 631
67.6 IPS
 
Image Classification (F16)
100% 610
65.3 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 932
5.76 IPS
 
Image Segmentation (F16)
100% 895
5.53 IPS
 
Image Segmentation (I8)
89% 1388
8.57 IPS
 
Pose Estimation (F32)
100% 350
1.42 IPS
 
Pose Estimation (F16)
100% 341
1.38 IPS
 
Pose Estimation (I8)
80% 423
1.71 IPS
 
Object Detection (F32)
100% 836
29.3 IPS
 
Object Detection (F16)
100% 847
29.7 IPS
 
Object Detection (I8)
52% 756
26.5 IPS
 
Face Detection (F32)
100% 1037
11.9 IPS
 
Face Detection (F16)
100% 1009
11.6 IPS
 
Face Detection (I8)
75% 809
9.30 IPS
 
Text Classification (F32)
100% 2369
937.2 IPS
 
Text Classification (F16)
100% 2340
925.5 IPS
 
Machine Translation (F32)
100% 1676
258.4 IPS
 
Machine Translation (F16)
100% 1673
257.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download