Geekbench ML Score

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

Result Information

Upload Date September 17 2021 12:47 PM
Views 2

System Information

System Information
Operating System iOS 15.0
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% 780
83.6 IPS
 
Image Classification (F16)
100% 735
78.7 IPS
 
Image Classification (I8)
81% 467
50.0 IPS
 
Image Segmentation (F32)
100% 1053
6.50 IPS
 
Image Segmentation (F16)
100% 1019
6.29 IPS
 
Image Segmentation (I8)
89% 1451
8.96 IPS
 
Pose Estimation (F32)
100% 407
1.65 IPS
 
Pose Estimation (F16)
100% 396
1.60 IPS
 
Pose Estimation (I8)
80% 468
1.90 IPS
 
Object Detection (F32)
100% 1014
35.6 IPS
 
Object Detection (F16)
100% 1009
35.4 IPS
 
Object Detection (I8)
52% 766
26.9 IPS
 
Face Detection (F32)
100% 1269
14.6 IPS
 
Face Detection (F16)
100% 1239
14.2 IPS
 
Face Detection (I8)
75% 843
9.69 IPS
 
Text Classification (F32)
100% 1172
463.4 IPS
 
Text Classification (F16)
100% 1285
508.3 IPS
 
Machine Translation (F32)
100% 1975
304.3 IPS
 
Machine Translation (F16)
100% 1966
302.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download