Geekbench ML Score

363
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 05:19 AM
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 315
33.7 IPS
 
Image Classification (F16)
100% 289
31.0 IPS
 
Image Classification (I8)
81% 207
22.2 IPS
 
Image Segmentation (F32)
100% 544
3.36 IPS
 
Image Segmentation (F16)
100% 552
3.41 IPS
 
Image Segmentation (I8)
89% 826
5.10 IPS
 
Pose Estimation (F32)
100% 253
1.03 IPS
 
Pose Estimation (F16)
100% 211
0.86 IPS
 
Pose Estimation (I8)
80% 235
0.95 IPS
 
Object Detection (F32)
100% 377
13.2 IPS
 
Object Detection (F16)
100% 336
11.8 IPS
 
Object Detection (I8)
52% 242
8.48 IPS
 
Face Detection (F32)
100% 491
5.64 IPS
 
Face Detection (F16)
100% 463
5.31 IPS
 
Face Detection (I8)
75% 431
4.95 IPS
 
Text Classification (F32)
100% 340
134.3 IPS
 
Text Classification (F16)
100% 338
133.6 IPS
 
Machine Translation (F32)
100% 473
73.0 IPS
 
Machine Translation (F16)
100% 478
73.6 IPS
 

Compare

Set Baseline