Geekbench ML Score

914
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 09:07 PM
Views 1

System Information

System Information
Operating System iOS 15.0
Model iPhone14,5
Model IDiPhone14,5
Motherboard D17AP
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 3.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 789
84.6 IPS
 
Image Classification (F16)
100% 757
81.1 IPS
 
Image Classification (I8)
81% 460
49.2 IPS
 
Image Segmentation (F32)
100% 1079
6.66 IPS
 
Image Segmentation (F16)
100% 1049
6.48 IPS
 
Image Segmentation (I8)
89% 1458
9.01 IPS
 
Pose Estimation (F32)
100% 413
1.67 IPS
 
Pose Estimation (F16)
100% 408
1.65 IPS
 
Pose Estimation (I8)
80% 478
1.94 IPS
 
Object Detection (F32)
100% 1049
36.8 IPS
 
Object Detection (F16)
100% 1064
37.3 IPS
 
Object Detection (I8)
52% 770
27.0 IPS
 
Face Detection (F32)
100% 1308
15.0 IPS
 
Face Detection (F16)
100% 1273
14.6 IPS
 
Face Detection (I8)
75% 853
9.80 IPS
 
Text Classification (F32)
100% 1003
396.8 IPS
 
Text Classification (F16)
100% 1063
420.6 IPS
 
Machine Translation (F32)
100% 1957
301.5 IPS
 
Machine Translation (F16)
100% 1975
304.3 IPS
 

Compare

Set Baseline Geekbench 6 now available