Geekbench ML Score

523
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 04:01 PM
Views 1

System Information

System Information
Operating System iOS 15.5
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 Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.67 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 377
40.4 IPS
 
Image Classification (F16)
100% 364
39.0 IPS
 
Image Classification (I8)
81% 235
25.2 IPS
 
Image Segmentation (F32)
100% 656
4.06 IPS
 
Image Segmentation (F16)
100% 623
3.85 IPS
 
Image Segmentation (I8)
89% 933
5.76 IPS
 
Pose Estimation (F32)
100% 231
0.93 IPS
 
Pose Estimation (F16)
100% 220
0.89 IPS
 
Pose Estimation (I8)
80% 254
1.03 IPS
 
Object Detection (F32)
100% 644
22.6 IPS
 
Object Detection (F16)
100% 647
22.7 IPS
 
Object Detection (I8)
52% 518
18.2 IPS
 
Face Detection (F32)
100% 807
9.27 IPS
 
Face Detection (F16)
100% 782
8.99 IPS
 
Face Detection (I8)
75% 523
6.01 IPS
 
Text Classification (F32)
100% 705
278.8 IPS
 
Text Classification (F16)
100% 697
275.8 IPS
 
Machine Translation (F32)
100% 929
143.1 IPS
 
Machine Translation (F16)
100% 882
135.9 IPS
 

Compare

Set Baseline