Geekbench ML Score

993
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 07:01 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.43 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 818
87.6 IPS
 
Image Classification (F16)
100% 812
87.0 IPS
 
Image Classification (I8)
81% 473
50.7 IPS
 
Image Segmentation (F32)
100% 1253
7.74 IPS
 
Image Segmentation (F16)
100% 1218
7.52 IPS
 
Image Segmentation (I8)
89% 1501
9.27 IPS
 
Pose Estimation (F32)
100% 469
1.90 IPS
 
Pose Estimation (F16)
100% 463
1.87 IPS
 
Pose Estimation (I8)
80% 527
2.13 IPS
 
Object Detection (F32)
100% 1167
41.0 IPS
 
Object Detection (F16)
100% 1215
42.6 IPS
 
Object Detection (I8)
52% 760
26.7 IPS
 
Face Detection (F32)
100% 1499
17.2 IPS
 
Face Detection (F16)
100% 1465
16.8 IPS
 
Face Detection (I8)
75% 863
9.92 IPS
 
Text Classification (F32)
100% 1036
409.6 IPS
 
Text Classification (F16)
100% 1020
403.3 IPS
 
Machine Translation (F32)
100% 2238
345.0 IPS
 
Machine Translation (F16)
100% 2236
344.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download