Geekbench ML Score

721
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 08:36 PM
Views 4

System Information

System Information
Operating System iOS 15.0.2
Model iPhone14,2
Model IDiPhone14,2
Motherboard D63AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.38 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 494
52.9 IPS
 
Image Classification (F16)
100% 482
51.7 IPS
 
Image Classification (I8)
81% 845
90.6 IPS
 
Image Segmentation (F32)
100% 574
3.54 IPS
 
Image Segmentation (F16)
100% 574
3.54 IPS
 
Image Segmentation (I8)
89% 1427
8.81 IPS
 
Pose Estimation (F32)
100% 252
1.02 IPS
 
Pose Estimation (F16)
100% 335
1.35 IPS
 
Pose Estimation (I8)
80% 386
1.56 IPS
 
Object Detection (F32)
100% 742
26.0 IPS
 
Object Detection (F16)
100% 752
26.4 IPS
 
Object Detection (I8)
52% 1091
38.3 IPS
 
Face Detection (F32)
100% 845
9.70 IPS
 
Face Detection (F16)
100% 857
9.85 IPS
 
Face Detection (I8)
75% 1146
13.2 IPS
 
Text Classification (F32)
100% 1239
490.2 IPS
 
Text Classification (F16)
100% 1218
481.8 IPS
 
Machine Translation (F32)
100% 930
143.3 IPS
 
Machine Translation (F16)
100% 932
143.6 IPS
 

Compare

Set Baseline Geekbench 6 now available