Geekbench ML Score

916
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:10 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone14,4
Model IDiPhone14,4
Motherboard D16AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.61 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 775
83.0 IPS
 
Image Classification (F16)
100% 736
78.9 IPS
 
Image Classification (I8)
81% 463
49.6 IPS
 
Image Segmentation (F32)
100% 1059
6.54 IPS
 
Image Segmentation (F16)
100% 1026
6.34 IPS
 
Image Segmentation (I8)
89% 1453
8.98 IPS
 
Pose Estimation (F32)
100% 403
1.63 IPS
 
Pose Estimation (F16)
100% 394
1.59 IPS
 
Pose Estimation (I8)
80% 464
1.88 IPS
 
Object Detection (F32)
100% 1016
35.7 IPS
 
Object Detection (F16)
100% 1017
35.7 IPS
 
Object Detection (I8)
52% 757
26.6 IPS
 
Face Detection (F32)
100% 1278
14.7 IPS
 
Face Detection (F16)
100% 1235
14.2 IPS
 
Face Detection (I8)
75% 841
9.66 IPS
 
Text Classification (F32)
100% 1247
493.0 IPS
 
Text Classification (F16)
100% 1227
485.4 IPS
 
Machine Translation (F32)
100% 1976
304.5 IPS
 
Machine Translation (F16)
100% 1970
303.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download