Geekbench ML Score

410
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 24 2021 01:11 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone X
Model IDiPhone10,6
Motherboard D221AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.76 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 380
40.7 IPS
 
Image Classification (F16)
100% 375
40.2 IPS
 
Image Classification (I8)
81% 285
30.6 IPS
 
Image Segmentation (F32)
100% 638
3.94 IPS
 
Image Segmentation (F16)
100% 612
3.78 IPS
 
Image Segmentation (I8)
89% 413
2.55 IPS
 
Pose Estimation (F32)
100% 92
0.37 IPS
 
Pose Estimation (F16)
100% 99
0.40 IPS
 
Pose Estimation (I8)
80% 165
0.67 IPS
 
Object Detection (F32)
100% 359
12.6 IPS
 
Object Detection (F16)
100% 443
15.5 IPS
 
Object Detection (I8)
52% 478
16.8 IPS
 
Face Detection (F32)
100% 634
7.29 IPS
 
Face Detection (F16)
100% 642
7.37 IPS
 
Face Detection (I8)
75% 587
6.75 IPS
 
Text Classification (F32)
100% 635
251.1 IPS
 
Text Classification (F16)
100% 694
274.5 IPS
 
Machine Translation (F32)
100% 752
116.0 IPS
 
Machine Translation (F16)
100% 743
114.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download