Geekbench ML Score

301
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date November 18 2024 09:42 AM
Views 2

System Information

System Information
Operating System Android 15
Model realme RMX5010
Model IDrealme RMX5010
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.32 GHz
Memory Information
Size 10.86 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 130
24.4 IPS
 
Image Classification (F16)
100% 129
24.1 IPS
 
Image Classification (I8)
97% 330
61.7 IPS
 
Image Segmentation (F32)
100% 162
2.70 IPS
 
Image Segmentation (F16)
100% 161
2.69 IPS
 
Image Segmentation (I8)
98% 330
5.51 IPS
 
Pose Estimation (F32)
100% 223
0.27 IPS
 
Pose Estimation (F16)
100% 223
0.27 IPS
 
Pose Estimation (I8)
100% 824
1.00 IPS
 
Object Detection (F32)
100% 136
10.2 IPS
 
Object Detection (F16)
100% 136
10.1 IPS
 
Object Detection (I8)
61% 338
25.3 IPS
 
Face Detection (F32)
100% 357
4.25 IPS
 
Face Detection (F16)
100% 356
4.23 IPS
 
Face Detection (I8)
86% 784
9.32 IPS
 
Depth Estimation (F32)
100% 302
2.34 IPS
 
Depth Estimation (F16)
100% 303
2.35 IPS
 
Depth Estimation (I8)
95% 842
6.53 IPS
 
Style Transfer (F32)
100% 555
0.73 IPS
 
Style Transfer (F16)
100% 552
0.73 IPS
 
Style Transfer (I8)
98% 1540
2.03 IPS
 
Image Super-Resolution (F32)
100% 155
5.55 IPS
 
Image Super-Resolution (F16)
100% 151
5.39 IPS
 
Image Super-Resolution (I8)
98% 598
21.4 IPS
 
Text Classification (F32)
100% 174
250.7 IPS
 
Text Classification (F16)
100% 172
246.5 IPS
 
Text Classification (I8)
92% 290
416.3 IPS
 
Machine Translation (F32)
100% 337
6.20 IPS
 
Machine Translation (F16)
100% 342
6.28 IPS
 
Machine Translation (I8)
64% 373
6.86 IPS
 

Compare

Set Baseline Geekbench 6 now available