Geekbench ML Score

486
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2024 08:48 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% 310
33.2 IPS
 
Image Classification (F16)
100% 539
57.8 IPS
 
Image Classification (I8)
80% 513
54.9 IPS
 
Image Segmentation (F32)
100% 649
4.01 IPS
 
Image Segmentation (F16)
100% 1176
7.26 IPS
 
Image Segmentation (I8)
89% 1200
7.41 IPS
 
Pose Estimation (F32)
100% 225
0.91 IPS
 
Pose Estimation (F16)
100% 518
2.09 IPS
 
Pose Estimation (I8)
80% 530
2.14 IPS
 
Object Detection (F32)
100% 283
9.92 IPS
 
Object Detection (F16)
100% 439
15.4 IPS
 
Object Detection (I8)
54% 464
16.3 IPS
 
Face Detection (F32)
100% 624
7.17 IPS
 
Face Detection (F16)
97% 1163
13.4 IPS
 
Face Detection (I8)
75% 1032
11.9 IPS
 
Text Classification (F32)
100% 407
160.8 IPS
 
Text Classification (F16)
98% 296
117.3 IPS
 
Machine Translation (F32)
100% 205
31.6 IPS
 
Machine Translation (F16)
100% 216
33.4 IPS
 

Compare

Set Baseline Geekbench 6 now available