Geekbench ML Score

720
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 10:31 PM
Views 1

System Information

System Information
Operating System iOS 15.0
Model iPhone14,3
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.37 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 456
48.9 IPS
 
Image Classification (F16)
100% 441
47.3 IPS
 
Image Classification (I8)
81% 866
92.7 IPS
 
Image Segmentation (F32)
100% 556
3.43 IPS
 
Image Segmentation (F16)
100% 558
3.44 IPS
 
Image Segmentation (I8)
89% 1494
9.23 IPS
 
Pose Estimation (F32)
100% 332
1.34 IPS
 
Pose Estimation (F16)
100% 336
1.36 IPS
 
Pose Estimation (I8)
80% 385
1.56 IPS
 
Object Detection (F32)
100% 726
25.5 IPS
 
Object Detection (F16)
100% 727
25.5 IPS
 
Object Detection (I8)
52% 1111
39.0 IPS
 
Face Detection (F32)
100% 851
9.78 IPS
 
Face Detection (F16)
100% 848
9.75 IPS
 
Face Detection (I8)
75% 1150
13.2 IPS
 
Text Classification (F32)
100% 1188
469.7 IPS
 
Text Classification (F16)
100% 1181
467.2 IPS
 
Machine Translation (F32)
100% 914
140.9 IPS
 
Machine Translation (F16)
100% 909
140.1 IPS
 

Compare

Set Baseline Geekbench 6 now available