Geekbench ML Score

206
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 08:43 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% 93
9.94 IPS
 
Image Classification (F16)
100% 95
10.2 IPS
 
Image Classification (I8)
81% 131
14.0 IPS
 
Image Segmentation (F32)
100% 346
2.14 IPS
 
Image Segmentation (F16)
100% 352
2.17 IPS
 
Image Segmentation (I8)
89% 530
3.27 IPS
 
Pose Estimation (F32)
100% 134
0.54 IPS
 
Pose Estimation (F16)
100% 135
0.55 IPS
 
Pose Estimation (I8)
80% 144
0.58 IPS
 
Object Detection (F32)
100% 155
5.44 IPS
 
Object Detection (F16)
100% 151
5.30 IPS
 
Object Detection (I8)
52% 220
7.73 IPS
 
Face Detection (F32)
100% 299
3.44 IPS
 
Face Detection (F16)
100% 302
3.47 IPS
 
Face Detection (I8)
75% 319
3.67 IPS
 
Text Classification (F32)
100% 276
109.2 IPS
 
Text Classification (F16)
100% 281
111.3 IPS
 
Machine Translation (F32)
100% 211
32.6 IPS
 
Machine Translation (F16)
100% 210
32.4 IPS
 

Compare

Set Baseline Geekbench 6 now available