Geekbench ML Score

892
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 13 2021 07:49 AM
Views 1

System Information

System Information
Operating System iOS 14.6
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
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 3.63 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 619
66.3 IPS
 
Image Classification (F16)
100% 608
65.2 IPS
 
Image Classification (I8)
81% 440
47.2 IPS
 
Image Segmentation (F32)
100% 956
5.91 IPS
 
Image Segmentation (F16)
100% 943
5.83 IPS
 
Image Segmentation (I8)
89% 1404
8.67 IPS
 
Pose Estimation (F32)
100% 367
1.49 IPS
 
Pose Estimation (F16)
100% 363
1.47 IPS
 
Pose Estimation (I8)
80% 437
1.77 IPS
 
Object Detection (F32)
100% 920
32.3 IPS
 
Object Detection (F16)
100% 927
32.5 IPS
 
Object Detection (I8)
52% 751
26.4 IPS
 
Face Detection (F32)
100% 1080
12.4 IPS
 
Face Detection (F16)
100% 1069
12.3 IPS
 
Face Detection (I8)
75% 815
9.36 IPS
 
Text Classification (F32)
100% 2340
925.7 IPS
 
Text Classification (F16)
100% 2375
939.2 IPS
 
Machine Translation (F32)
100% 1688
260.1 IPS
 
Machine Translation (F16)
100% 1687
260.1 IPS
 

Compare

Set Baseline Geekbench 6 now available