Geekbench ML Score

551
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:33 AM
Views 3

System Information

System Information
Operating System iOS 14.8
Model iPhone XS Max
Model IDiPhone11,6
Motherboard D331pAP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 465
49.9 IPS
 
Image Classification (F16)
100% 453
48.5 IPS
 
Image Classification (I8)
81% 259
27.7 IPS
 
Image Segmentation (F32)
100% 757
4.67 IPS
 
Image Segmentation (F16)
100% 741
4.58 IPS
 
Image Segmentation (I8)
89% 952
5.88 IPS
 
Pose Estimation (F32)
100% 177
0.72 IPS
 
Pose Estimation (F16)
100% 204
0.83 IPS
 
Pose Estimation (I8)
80% 250
1.01 IPS
 
Object Detection (F32)
100% 667
23.4 IPS
 
Object Detection (F16)
100% 668
23.4 IPS
 
Object Detection (I8)
52% 516
18.1 IPS
 
Face Detection (F32)
100% 795
9.13 IPS
 
Face Detection (F16)
100% 798
9.17 IPS
 
Face Detection (I8)
75% 581
6.68 IPS
 
Text Classification (F32)
100% 746
294.9 IPS
 
Text Classification (F16)
100% 752
297.6 IPS
 
Machine Translation (F32)
100% 994
153.3 IPS
 
Machine Translation (F16)
100% 993
153.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download