Geekbench ML Score

407
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 07 2024 12:54 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 3.36 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% 594
63.7 IPS
 
Image Classification (I8)
80% 663
71.0 IPS
 
Image Segmentation (F32)
100% 387
2.39 IPS
 
Image Segmentation (F16)
100% 535
3.30 IPS
 
Image Segmentation (I8)
89% 1145
7.07 IPS
 
Pose Estimation (F32)
100% 252
1.02 IPS
 
Pose Estimation (F16)
100% 566
2.29 IPS
 
Pose Estimation (I8)
80% 354
1.43 IPS
 
Object Detection (F32)
100% 310
10.9 IPS
 
Object Detection (F16)
99% 540
18.9 IPS
 
Object Detection (I8)
53% 449
15.8 IPS
 
Face Detection (F32)
25% 529
6.08 IPS
 
Face Detection (F16)
25% 747
8.58 IPS
 
Face Detection (I8)
75% 824
9.47 IPS
 
Text Classification (F32)
100% 195
77.0 IPS
 
Text Classification (F16)
100% 209
82.5 IPS
 
Machine Translation (F32)
100% 206
31.7 IPS
 
Machine Translation (F16)
100% 207
31.8 IPS
 

Compare

Set Baseline Geekbench 6 now available