Geekbench ML Score

266
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date April 27 2024 04:38 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 23108RN04Y
Model IDXiaomi 23108RN04Y
Motherboard gust
CPU Information
Name ARM MT6769V/CZ
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.00 GHz
Memory Information
Size 7.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 115
21.5 IPS
 
Image Classification (F16)
100% 121
22.7 IPS
 
Image Classification (I8)
97% 242
45.2 IPS
 
Image Segmentation (F32)
100% 181
3.02 IPS
 
Image Segmentation (F16)
100% 178
2.98 IPS
 
Image Segmentation (I8)
98% 267
4.47 IPS
 
Pose Estimation (F32)
100% 250
0.30 IPS
 
Pose Estimation (F16)
100% 242
0.29 IPS
 
Pose Estimation (I8)
100% 1073
1.30 IPS
 
Object Detection (F32)
100% 123
9.15 IPS
 
Object Detection (F16)
100% 123
9.21 IPS
 
Object Detection (I8)
61% 328
24.5 IPS
 
Face Detection (F32)
100% 292
3.47 IPS
 
Face Detection (F16)
100% 303
3.60 IPS
 
Face Detection (I8)
86% 631
7.51 IPS
 
Depth Estimation (F32)
100% 280
2.17 IPS
 
Depth Estimation (F16)
100% 272
2.11 IPS
 
Depth Estimation (I8)
95% 655
5.08 IPS
 
Style Transfer (F32)
100% 478
0.63 IPS
 
Style Transfer (F16)
100% 466
0.61 IPS
 
Style Transfer (I8)
98% 1255
1.65 IPS
 
Image Super-Resolution (F32)
100% 178
6.37 IPS
 
Image Super-Resolution (F16)
100% 150
5.37 IPS
 
Image Super-Resolution (I8)
98% 564
20.1 IPS
 
Text Classification (F32)
100% 193
278.1 IPS
 
Text Classification (F16)
100% 149
213.7 IPS
 
Text Classification (I8)
92% 157
225.3 IPS
 
Machine Translation (F32)
100% 275
5.06 IPS
 
Machine Translation (F16)
100% 251
4.62 IPS
 
Machine Translation (I8)
64% 166
3.05 IPS
 

Compare

Set Baseline Geekbench 6 now available