Geekbench ML Score

738
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 05:28 PM
Views 1

System Information

System Information
Operating System Android 12
Model realme RMX3363
Model IDrealme RMX3363
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 5.16 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 511
54.8 IPS
 
Image Classification (F16)
100% 896
96.0 IPS
 
Image Classification (I8)
79% 2892
309.9 IPS
 
Image Segmentation (F32)
100% 1121
6.93 IPS
 
Image Segmentation (F16)
100% 1843
11.4 IPS
 
Image Segmentation (I8)
89% 328
2.02 IPS
 
Pose Estimation (F32)
100% 261
1.06 IPS
 
Pose Estimation (F16)
100% 910
3.68 IPS
 
Pose Estimation (I8)
80% 10002
40.5 IPS
 
Object Detection (F32)
100% 532
18.7 IPS
 
Object Detection (F16)
100% 675
23.7 IPS
 
Object Detection (I8)
56% 1146
40.2 IPS
 
Face Detection (F32)
100% 800
9.19 IPS
 
Face Detection (F16)
97% 1272
14.6 IPS
 
Face Detection (I8)
76% 13472
154.8 IPS
 
Text Classification (F32)
100% 9
3.54 IPS
 
Text Classification (F16)
100% 170
67.1 IPS
 
Machine Translation (F32)
100% 414
63.8 IPS
 
Machine Translation (F16)
100% 415
64.0 IPS
 

Compare

Set Baseline