Geekbench ML Score

383
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 22 2024 01:35 AM
Views 7

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 7.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 199
21.3 IPS
 
Image Classification (F16)
100% 592
63.4 IPS
 
Image Classification (I8)
80% 506
54.2 IPS
 
Image Segmentation (F32)
100% 380
2.34 IPS
 
Image Segmentation (F16)
100% 522
3.22 IPS
 
Image Segmentation (I8)
89% 1017
6.28 IPS
 
Pose Estimation (F32)
100% 252
1.02 IPS
 
Pose Estimation (F16)
100% 570
2.31 IPS
 
Pose Estimation (I8)
80% 320
1.29 IPS
 
Object Detection (F32)
100% 301
10.6 IPS
 
Object Detection (F16)
99% 519
18.2 IPS
 
Object Detection (I8)
53% 327
11.5 IPS
 
Face Detection (F32)
25% 532
6.11 IPS
 
Face Detection (F16)
25% 755
8.68 IPS
 
Face Detection (I8)
75% 647
7.43 IPS
 
Text Classification (F32)
100% 170
67.3 IPS
 
Text Classification (F16)
100% 245
96.8 IPS
 
Machine Translation (F32)
100% 201
31.0 IPS
 
Machine Translation (F16)
100% 202
31.2 IPS
 

Compare

Set Baseline Geekbench 6 now available