Geekbench ML Score

893
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 08 2023 06:31 AM
Views 1

System Information

System Information
Operating System Android 13
Model motorola motorola edge 40
Model IDmotorola motorola edge 40
Motherboard lyriq
CPU Information
Name ARM MT6891Z_Z/CZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.60 GHz
Memory Information
Size 7.29 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 638
68.3 IPS
 
Image Classification (F16)
100% 660
70.7 IPS
 
Image Classification (I8)
80% 608
65.1 IPS
 
Image Segmentation (F32)
100% 1855
11.5 IPS
 
Image Segmentation (F16)
100% 3309
20.4 IPS
 
Image Segmentation (I8)
89% 3288
20.3 IPS
 
Pose Estimation (F32)
100% 634
2.57 IPS
 
Pose Estimation (F16)
100% 1857
7.52 IPS
 
Pose Estimation (I8)
80% 1782
7.21 IPS
 
Object Detection (F32)
100% 376
13.2 IPS
 
Object Detection (F16)
100% 612
21.5 IPS
 
Object Detection (I8)
54% 436
15.3 IPS
 
Face Detection (F32)
100% 1401
16.1 IPS
 
Face Detection (F16)
97% 2613
30.0 IPS
 
Face Detection (I8)
75% 2381
27.4 IPS
 
Text Classification (F32)
100% 529
209.2 IPS
 
Text Classification (F16)
98% 469
185.6 IPS
 
Machine Translation (F32)
100% 226
34.8 IPS
 
Machine Translation (F16)
100% 222
34.3 IPS
 

Compare

Set Baseline Geekbench 6 now available