Geekbench ML Score

428
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 07 2024 07:31 AM
Views 1

System Information

System Information
Operating System Android 14
Model vivo V2307
Model IDvivo V2307
Motherboard holi
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 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.02 GHz
Memory Information
Size 7.27 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 219
41.0 IPS
 
Image Classification (F16)
100% 199
37.1 IPS
 
Image Classification (I8)
97% 501
93.8 IPS
 
Image Segmentation (F32)
100% 276
4.62 IPS
 
Image Segmentation (F16)
100% 278
4.64 IPS
 
Image Segmentation (I8)
98% 416
6.94 IPS
 
Pose Estimation (F32)
100% 388
0.47 IPS
 
Pose Estimation (F16)
100% 379
0.46 IPS
 
Pose Estimation (I8)
100% 1913
2.32 IPS
 
Object Detection (F32)
100% 210
15.6 IPS
 
Object Detection (F16)
100% 218
16.3 IPS
 
Object Detection (I8)
61% 557
41.6 IPS
 
Face Detection (F32)
100% 438
5.21 IPS
 
Face Detection (F16)
100% 437
5.20 IPS
 
Face Detection (I8)
86% 1087
12.9 IPS
 
Depth Estimation (F32)
100% 423
3.28 IPS
 
Depth Estimation (F16)
100% 432
3.35 IPS
 
Depth Estimation (I8)
95% 1145
8.88 IPS
 
Style Transfer (F32)
100% 721
0.95 IPS
 
Style Transfer (F16)
100% 696
0.92 IPS
 
Style Transfer (I8)
98% 1733
2.28 IPS
 
Image Super-Resolution (F32)
100% 262
9.34 IPS
 
Image Super-Resolution (F16)
100% 261
9.31 IPS
 
Image Super-Resolution (I8)
98% 835
29.8 IPS
 
Text Classification (F32)
100% 239
343.9 IPS
 
Text Classification (F16)
100% 243
348.7 IPS
 
Text Classification (I8)
92% 226
325.4 IPS
 
Machine Translation (F32)
100% 505
9.29 IPS
 
Machine Translation (F16)
100% 495
9.11 IPS
 
Machine Translation (I8)
64% 252
4.63 IPS
 

Compare

Set Baseline Geekbench 6 now available