Geekbench ML Score

213
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 21 2024 01:41 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 7.30 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 90
9.66 IPS
 
Image Classification (F16)
100% 90
9.66 IPS
 
Image Classification (I8)
81% 153
16.3 IPS
 
Image Segmentation (F32)
100% 365
2.26 IPS
 
Image Segmentation (F16)
100% 362
2.24 IPS
 
Image Segmentation (I8)
89% 580
3.58 IPS
 
Pose Estimation (F32)
100% 138
0.56 IPS
 
Pose Estimation (F16)
100% 121
0.49 IPS
 
Pose Estimation (I8)
80% 147
0.60 IPS
 
Object Detection (F32)
100% 153
5.37 IPS
 
Object Detection (F16)
100% 162
5.68 IPS
 
Object Detection (I8)
52% 249
8.74 IPS
 
Face Detection (F32)
100% 316
3.63 IPS
 
Face Detection (F16)
100% 310
3.56 IPS
 
Face Detection (I8)
75% 366
4.20 IPS
 
Text Classification (F32)
100% 285
112.9 IPS
 
Text Classification (F16)
100% 285
112.6 IPS
 
Machine Translation (F32)
100% 203
31.2 IPS
 
Machine Translation (F16)
100% 209
32.2 IPS
 

Compare

Set Baseline Geekbench 6 now available