Geekbench ML Score

474
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 09 2024 10:06 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% 579
62.0 IPS
 
Image Classification (I8)
80% 531
56.9 IPS
 
Image Segmentation (F32)
100% 637
3.94 IPS
 
Image Segmentation (F16)
100% 1189
7.34 IPS
 
Image Segmentation (I8)
89% 1210
7.47 IPS
 
Pose Estimation (F32)
100% 227
0.92 IPS
 
Pose Estimation (F16)
100% 551
2.23 IPS
 
Pose Estimation (I8)
80% 549
2.22 IPS
 
Object Detection (F32)
100% 270
9.47 IPS
 
Object Detection (F16)
100% 410
14.4 IPS
 
Object Detection (I8)
54% 386
13.6 IPS
 
Face Detection (F32)
100% 640
7.36 IPS
 
Face Detection (F16)
97% 1224
14.1 IPS
 
Face Detection (I8)
75% 1113
12.8 IPS
 
Text Classification (F32)
100% 235
93.0 IPS
 
Text Classification (F16)
98% 331
130.8 IPS
 
Machine Translation (F32)
100% 193
29.7 IPS
 
Machine Translation (F16)
100% 210
32.4 IPS
 

Compare

Set Baseline Geekbench 6 now available