Geekbench ML Score

472
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 08:46 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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 315
33.8 IPS
 
Image Classification (F16)
100% 553
59.2 IPS
 
Image Classification (I8)
80% 533
57.2 IPS
 
Image Segmentation (F32)
100% 623
3.85 IPS
 
Image Segmentation (F16)
100% 1175
7.26 IPS
 
Image Segmentation (I8)
89% 1203
7.43 IPS
 
Pose Estimation (F32)
100% 223
0.90 IPS
 
Pose Estimation (F16)
100% 518
2.10 IPS
 
Pose Estimation (I8)
80% 533
2.16 IPS
 
Object Detection (F32)
100% 281
9.87 IPS
 
Object Detection (F16)
100% 438
15.4 IPS
 
Object Detection (I8)
54% 451
15.8 IPS
 
Face Detection (F32)
100% 627
7.20 IPS
 
Face Detection (F16)
97% 1158
13.3 IPS
 
Face Detection (I8)
75% 1107
12.7 IPS
 
Text Classification (F32)
100% 209
82.7 IPS
 
Text Classification (F16)
98% 307
121.6 IPS
 
Machine Translation (F32)
100% 211
32.5 IPS
 
Machine Translation (F16)
100% 214
33.0 IPS
 

Compare

Set Baseline Geekbench 6 now available