Geekbench ML Score

441
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 21 2025 11:48 PM
Views 3

System Information

System Information
Operating System Android 14
Model samsung SM-M166P
Model IDsamsung SM-M166P
Motherboard m16xm
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 3.33 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 283
30.3 IPS
 
Image Classification (F16)
100% 468
50.1 IPS
 
Image Classification (I8)
80% 439
47.0 IPS
 
Image Segmentation (F32)
100% 637
3.93 IPS
 
Image Segmentation (F16)
100% 1183
7.31 IPS
 
Image Segmentation (I8)
89% 1152
7.11 IPS
 
Pose Estimation (F32)
100% 231
0.94 IPS
 
Pose Estimation (F16)
100% 547
2.21 IPS
 
Pose Estimation (I8)
80% 518
2.09 IPS
 
Object Detection (F32)
100% 262
9.20 IPS
 
Object Detection (F16)
100% 389
13.7 IPS
 
Object Detection (I8)
54% 402
14.1 IPS
 
Face Detection (F32)
100% 623
7.16 IPS
 
Face Detection (F16)
97% 1097
12.6 IPS
 
Face Detection (I8)
75% 1022
11.7 IPS
 
Text Classification (F32)
100% 204
80.6 IPS
 
Text Classification (F16)
98% 239
94.4 IPS
 
Machine Translation (F32)
100% 201
31.0 IPS
 
Machine Translation (F16)
100% 193
29.8 IPS
 

Compare

Set Baseline Geekbench 6 now available