Geekbench ML Score

412
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 06 2024 11:44 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 3.36 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 199
21.4 IPS
 
Image Classification (F16)
100% 597
64.0 IPS
 
Image Classification (I8)
80% 645
69.1 IPS
 
Image Segmentation (F32)
100% 384
2.37 IPS
 
Image Segmentation (F16)
100% 547
3.38 IPS
 
Image Segmentation (I8)
89% 1199
7.40 IPS
 
Pose Estimation (F32)
100% 251
1.01 IPS
 
Pose Estimation (F16)
100% 568
2.30 IPS
 
Pose Estimation (I8)
80% 376
1.52 IPS
 
Object Detection (F32)
100% 309
10.9 IPS
 
Object Detection (F16)
99% 540
18.9 IPS
 
Object Detection (I8)
53% 458
16.1 IPS
 
Face Detection (F32)
25% 524
6.02 IPS
 
Face Detection (F16)
25% 746
8.57 IPS
 
Face Detection (I8)
75% 767
8.81 IPS
 
Text Classification (F32)
100% 203
80.3 IPS
 
Text Classification (F16)
100% 217
85.8 IPS
 
Machine Translation (F32)
100% 219
33.7 IPS
 
Machine Translation (F16)
100% 215
33.2 IPS
 

Compare

Set Baseline Geekbench 6 now available