Geekbench ML Score

367
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 02 2024 06:41 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 NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 198
21.2 IPS
 
Image Classification (F16)
100% 598
64.0 IPS
 
Image Classification (I8)
80% 649
69.5 IPS
 
Image Segmentation (F32)
100% 394
2.43 IPS
 
Image Segmentation (F16)
100% 525
3.24 IPS
 
Image Segmentation (I8)
89% 1111
6.86 IPS
 
Pose Estimation (F32)
100% 248
1.01 IPS
 
Pose Estimation (F16)
100% 561
2.27 IPS
 
Pose Estimation (I8)
80% 257
1.04 IPS
 
Object Detection (F32)
100% 294
10.3 IPS
 
Object Detection (F16)
99% 541
19.0 IPS
 
Object Detection (I8)
53% 441
15.5 IPS
 
Face Detection (F32)
25% 498
5.72 IPS
 
Face Detection (F16)
25% 738
8.48 IPS
 
Face Detection (I8)
75% 490
5.63 IPS
 
Text Classification (F32)
100% 129
51.1 IPS
 
Text Classification (F16)
100% 130
51.3 IPS
 
Machine Translation (F32)
100% 202
31.1 IPS
 
Machine Translation (F16)
100% 208
32.1 IPS
 

Compare

Set Baseline Geekbench 6 now available