Geekbench ML Score

727
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 29 2021 01:48 AM
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 1.38 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 469
50.2 IPS
 
Image Classification (F16)
100% 436
46.7 IPS
 
Image Classification (I8)
81% 910
97.5 IPS
 
Image Segmentation (F32)
100% 566
3.50 IPS
 
Image Segmentation (F16)
100% 563
3.48 IPS
 
Image Segmentation (I8)
89% 1496
9.24 IPS
 
Pose Estimation (F32)
100% 333
1.35 IPS
 
Pose Estimation (F16)
100% 333
1.35 IPS
 
Pose Estimation (I8)
80% 388
1.57 IPS
 
Object Detection (F32)
100% 724
25.4 IPS
 
Object Detection (F16)
100% 730
25.6 IPS
 
Object Detection (I8)
52% 1136
39.9 IPS
 
Face Detection (F32)
100% 853
9.80 IPS
 
Face Detection (F16)
100% 854
9.81 IPS
 
Face Detection (I8)
75% 1173
13.5 IPS
 
Text Classification (F32)
100% 1204
476.4 IPS
 
Text Classification (F16)
100% 1211
479.0 IPS
 
Machine Translation (F32)
100% 917
141.3 IPS
 
Machine Translation (F16)
100% 916
141.2 IPS
 

Compare

Set Baseline Geekbench 6 now available