Geekbench ML Score

372
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 09:36 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 3.38 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% 565
60.5 IPS
 
Image Classification (I8)
80% 505
54.1 IPS
 
Image Segmentation (F32)
100% 368
2.27 IPS
 
Image Segmentation (F16)
100% 520
3.21 IPS
 
Image Segmentation (I8)
89% 1000
6.18 IPS
 
Pose Estimation (F32)
100% 248
1.00 IPS
 
Pose Estimation (F16)
100% 562
2.27 IPS
 
Pose Estimation (I8)
80% 320
1.30 IPS
 
Object Detection (F32)
100% 299
10.5 IPS
 
Object Detection (F16)
99% 520
18.2 IPS
 
Object Detection (I8)
53% 357
12.5 IPS
 
Face Detection (F32)
25% 523
6.01 IPS
 
Face Detection (F16)
25% 732
8.42 IPS
 
Face Detection (I8)
75% 617
7.09 IPS
 
Text Classification (F32)
100% 167
66.2 IPS
 
Text Classification (F16)
100% 169
66.8 IPS
 
Machine Translation (F32)
100% 196
30.3 IPS
 
Machine Translation (F16)
100% 198
30.5 IPS
 

Compare

Set Baseline Geekbench 6 now available