Geekbench ML Score

203
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 10:11 AM
Views 1

System Information

System Information
Operating System iOS 14.8
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% 354
37.9 IPS
 
Image Classification (F16)
100% 299
32.0 IPS
 
Image Classification (I8)
81% 102
10.9 IPS
 
Image Segmentation (F32)
100% 251
1.55 IPS
 
Image Segmentation (F16)
100% 262
1.62 IPS
 
Image Segmentation (I8)
89% 405
2.50 IPS
 
Pose Estimation (F32)
100% 82
0.33 IPS
 
Pose Estimation (F16)
100% 64
0.26 IPS
 
Pose Estimation (I8)
80% 82
0.33 IPS
 
Object Detection (F32)
100% 202
7.08 IPS
 
Object Detection (F16)
100% 201
7.07 IPS
 
Object Detection (I8)
52% 186
6.53 IPS
 
Face Detection (F32)
100% 278
3.20 IPS
 
Face Detection (F16)
100% 241
2.77 IPS
 
Face Detection (I8)
75% 225
2.59 IPS
 
Text Classification (F32)
100% 229
90.6 IPS
 
Text Classification (F16)
100% 229
90.7 IPS
 
Machine Translation (F32)
100% 317
48.8 IPS
 
Machine Translation (F16)
100% 317
48.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download