Geekbench ML Score

211
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 31 2024 12:35 AM
Views 3

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 3.36 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 95
10.2 IPS
 
Image Classification (F16)
100% 91
9.74 IPS
 
Image Classification (I8)
81% 143
15.3 IPS
 
Image Segmentation (F32)
100% 352
2.18 IPS
 
Image Segmentation (F16)
100% 352
2.18 IPS
 
Image Segmentation (I8)
89% 546
3.37 IPS
 
Pose Estimation (F32)
100% 140
0.56 IPS
 
Pose Estimation (F16)
100% 135
0.55 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
100% 149
5.24 IPS
 
Object Detection (F16)
100% 156
5.48 IPS
 
Object Detection (I8)
52% 239
8.38 IPS
 
Face Detection (F32)
100% 303
3.48 IPS
 
Face Detection (F16)
100% 303
3.49 IPS
 
Face Detection (I8)
75% 363
4.17 IPS
 
Text Classification (F32)
100% 283
111.9 IPS
 
Text Classification (F16)
100% 289
114.3 IPS
 
Machine Translation (F32)
100% 205
31.7 IPS
 
Machine Translation (F16)
100% 219
33.7 IPS
 

Compare

Set Baseline Geekbench 6 now available