Geekbench ML Score

413
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 17 2024 03:23 AM
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 7.28 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 204
21.8 IPS
 
Image Classification (F16)
100% 606
64.9 IPS
 
Image Classification (I8)
80% 650
69.6 IPS
 
Image Segmentation (F32)
100% 395
2.44 IPS
 
Image Segmentation (F16)
100% 554
3.42 IPS
 
Image Segmentation (I8)
89% 1191
7.36 IPS
 
Pose Estimation (F32)
100% 253
1.02 IPS
 
Pose Estimation (F16)
100% 573
2.32 IPS
 
Pose Estimation (I8)
80% 372
1.51 IPS
 
Object Detection (F32)
100% 315
11.1 IPS
 
Object Detection (F16)
99% 546
19.2 IPS
 
Object Detection (I8)
53% 452
15.9 IPS
 
Face Detection (F32)
25% 545
6.26 IPS
 
Face Detection (F16)
25% 770
8.85 IPS
 
Face Detection (I8)
75% 768
8.83 IPS
 
Text Classification (F32)
100% 208
82.3 IPS
 
Text Classification (F16)
100% 210
83.1 IPS
 
Machine Translation (F32)
100% 204
31.5 IPS
 
Machine Translation (F16)
100% 208
32.0 IPS
 

Compare

Set Baseline Geekbench 6 now available