Geekbench ML Score

928
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 14 2023 01:09 AM
Views 1

System Information

System Information
Operating System iOS 17.0
Model iPhone 13 mini
Model IDiPhone14,4
Motherboard D16AP
CPU Information
Name Apple A15 Bionic
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 3.57 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 798
85.5 IPS
 
Image Classification (F16)
100% 765
81.9 IPS
 
Image Classification (I8)
81% 473
50.7 IPS
 
Image Segmentation (F32)
100% 1124
6.94 IPS
 
Image Segmentation (F16)
100% 1072
6.62 IPS
 
Image Segmentation (I8)
89% 1455
8.99 IPS
 
Pose Estimation (F32)
100% 410
1.66 IPS
 
Pose Estimation (F16)
100% 403
1.63 IPS
 
Pose Estimation (I8)
80% 471
1.91 IPS
 
Object Detection (F32)
100% 1047
36.7 IPS
 
Object Detection (F16)
100% 1060
37.2 IPS
 
Object Detection (I8)
52% 746
26.2 IPS
 
Face Detection (F32)
100% 1311
15.1 IPS
 
Face Detection (F16)
100% 1275
14.6 IPS
 
Face Detection (I8)
75% 854
9.81 IPS
 
Text Classification (F32)
100% 1087
430.0 IPS
 
Text Classification (F16)
100% 1138
450.3 IPS
 
Machine Translation (F32)
100% 2059
317.4 IPS
 
Machine Translation (F16)
100% 2050
315.9 IPS
 

Compare

Set Baseline Geekbench 6 now available