Geekbench ML Score

277
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 19 2024 04:25 AM
Views 2

System Information

System Information
Operating System Android 14
Model Xiaomi 23129RA5FL
Model IDXiaomi 23129RA5FL
Motherboard bengal
Governorwalt
CPU Information
Name ARM ARMv8
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 @ 2.80 GHz
Memory Information
Size 5.47 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 149
27.9 IPS
 
Image Classification (F16)
100% 150
28.1 IPS
 
Image Classification (I8)
97% 242
45.2 IPS
 
Image Segmentation (F32)
100% 207
3.45 IPS
 
Image Segmentation (F16)
100% 200
3.34 IPS
 
Image Segmentation (I8)
98% 259
4.32 IPS
 
Pose Estimation (F32)
100% 284
0.34 IPS
 
Pose Estimation (F16)
100% 285
0.35 IPS
 
Pose Estimation (I8)
100% 802
0.97 IPS
 
Object Detection (F32)
100% 157
11.7 IPS
 
Object Detection (F16)
100% 156
11.6 IPS
 
Object Detection (I8)
61% 269
20.1 IPS
 
Face Detection (F32)
100% 312
3.71 IPS
 
Face Detection (F16)
100% 317
3.76 IPS
 
Face Detection (I8)
86% 549
6.53 IPS
 
Depth Estimation (F32)
100% 294
2.28 IPS
 
Depth Estimation (F16)
100% 293
2.27 IPS
 
Depth Estimation (I8)
95% 566
4.39 IPS
 
Style Transfer (F32)
100% 441
0.58 IPS
 
Style Transfer (F16)
100% 463
0.61 IPS
 
Style Transfer (I8)
98% 1152
1.52 IPS
 
Image Super-Resolution (F32)
100% 168
6.01 IPS
 
Image Super-Resolution (F16)
100% 165
5.91 IPS
 
Image Super-Resolution (I8)
98% 389
13.9 IPS
 
Text Classification (F32)
100% 193
277.6 IPS
 
Text Classification (F16)
100% 192
275.9 IPS
 
Text Classification (I8)
92% 148
212.6 IPS
 
Machine Translation (F32)
100% 324
5.96 IPS
 
Machine Translation (F16)
100% 336
6.18 IPS
 
Machine Translation (I8)
64% 194
3.56 IPS
 

Compare

Set Baseline Geekbench 6 now available