Geekbench ML Score

343
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 09:24 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 NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 193
20.7 IPS
 
Image Classification (F16)
100% 542
58.0 IPS
 
Image Classification (I8)
80% 555
59.5 IPS
 
Image Segmentation (F32)
100% 366
2.26 IPS
 
Image Segmentation (F16)
100% 489
3.02 IPS
 
Image Segmentation (I8)
89% 989
6.11 IPS
 
Pose Estimation (F32)
100% 252
1.02 IPS
 
Pose Estimation (F16)
100% 557
2.25 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 285
10.0 IPS
 
Object Detection (F16)
99% 507
17.8 IPS
 
Object Detection (I8)
53% 290
10.2 IPS
 
Face Detection (F32)
25% 496
5.70 IPS
 
Face Detection (F16)
25% 718
8.25 IPS
 
Face Detection (I8)
75% 460
5.29 IPS
 
Text Classification (F32)
100% 160
63.4 IPS
 
Text Classification (F16)
100% 128
50.6 IPS
 
Machine Translation (F32)
100% 174
26.8 IPS
 
Machine Translation (F16)
100% 177
27.2 IPS
 

Compare

Set Baseline Geekbench 6 now available