Geekbench ML Score

205
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 09:39 PM
Views 1

System Information

System Information
Operating System Android 14
Model samsung SM-A166P
Model IDsamsung SM-A166P
Motherboard a16xm
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 3.38 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 96
10.3 IPS
 
Image Classification (F16)
100% 91
9.75 IPS
 
Image Classification (I8)
81% 141
15.1 IPS
 
Image Segmentation (F32)
100% 341
2.11 IPS
 
Image Segmentation (F16)
100% 344
2.13 IPS
 
Image Segmentation (I8)
89% 536
3.31 IPS
 
Pose Estimation (F32)
100% 131
0.53 IPS
 
Pose Estimation (F16)
100% 129
0.52 IPS
 
Pose Estimation (I8)
80% 146
0.59 IPS
 
Object Detection (F32)
100% 155
5.44 IPS
 
Object Detection (F16)
100% 149
5.24 IPS
 
Object Detection (I8)
52% 218
7.65 IPS
 
Face Detection (F32)
100% 298
3.42 IPS
 
Face Detection (F16)
100% 298
3.42 IPS
 
Face Detection (I8)
75% 321
3.68 IPS
 
Text Classification (F32)
100% 272
107.5 IPS
 
Text Classification (F16)
100% 270
106.6 IPS
 
Machine Translation (F32)
100% 215
33.1 IPS
 
Machine Translation (F16)
100% 212
32.6 IPS
 

Compare

Set Baseline Geekbench 6 now available