Geekbench ML Score

218
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 19 2024 12:35 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 220333QNY
Model IDXiaomi 220333QNY
Motherboard rain
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3337 revision 0
Base Frequency 1.90 GHz
Cluster 14 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 112
21.0 IPS
 
Image Classification (F16)
100% 115
21.5 IPS
 
Image Classification (I8)
97% 180
33.7 IPS
 
Image Segmentation (F32)
100% 177
2.96 IPS
 
Image Segmentation (F16)
100% 177
2.95 IPS
 
Image Segmentation (I8)
98% 216
3.61 IPS
 
Pose Estimation (F32)
100% 234
0.28 IPS
 
Pose Estimation (F16)
100% 233
0.28 IPS
 
Pose Estimation (I8)
100% 693
0.84 IPS
 
Object Detection (F32)
100% 127
9.47 IPS
 
Object Detection (F16)
100% 125
9.35 IPS
 
Object Detection (I8)
61% 216
16.1 IPS
 
Face Detection (F32)
100% 275
3.27 IPS
 
Face Detection (F16)
100% 274
3.26 IPS
 
Face Detection (I8)
86% 468
5.56 IPS
 
Depth Estimation (F32)
100% 253
1.96 IPS
 
Depth Estimation (F16)
100% 249
1.93 IPS
 
Depth Estimation (I8)
95% 472
3.66 IPS
 
Style Transfer (F32)
100% 424
0.56 IPS
 
Style Transfer (F16)
100% 413
0.54 IPS
 
Style Transfer (I8)
98% 981
1.29 IPS
 
Image Super-Resolution (F32)
100% 146
5.21 IPS
 
Image Super-Resolution (F16)
100% 145
5.18 IPS
 
Image Super-Resolution (I8)
98% 317
11.3 IPS
 
Text Classification (F32)
100% 108
155.6 IPS
 
Text Classification (F16)
100% 103
147.5 IPS
 
Text Classification (I8)
92% 95
136.9 IPS
 
Machine Translation (F32)
100% 215
3.95 IPS
 
Machine Translation (F16)
100% 218
4.02 IPS
 
Machine Translation (I8)
64% 124
2.29 IPS
 

Compare

Set Baseline Geekbench 6 now available