Geekbench ML Score

1638
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 24 2024 06:24 PM
Views 3

System Information

System Information
Operating System Android 15
Model OnePlus PJZ110
Model IDOnePlus PJZ110
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.32 GHz
Memory Information
Size 14.75 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 933
174.6 IPS
 
Image Classification (F16)
100% 1070
200.2 IPS
 
Image Classification (I8)
97% 1542
288.5 IPS
 
Image Segmentation (F32)
100% 1390
23.2 IPS
 
Image Segmentation (F16)
100% 1400
23.4 IPS
 
Image Segmentation (I8)
98% 1516
25.3 IPS
 
Pose Estimation (F32)
100% 1853
2.24 IPS
 
Pose Estimation (F16)
100% 1849
2.24 IPS
 
Pose Estimation (I8)
100% 8525
10.3 IPS
 
Object Detection (F32)
100% 1051
78.4 IPS
 
Object Detection (F16)
100% 1143
85.3 IPS
 
Object Detection (I8)
61% 2198
164.1 IPS
 
Face Detection (F32)
100% 2014
24.0 IPS
 
Face Detection (F16)
100% 2013
23.9 IPS
 
Face Detection (I8)
86% 3702
44.0 IPS
 
Depth Estimation (F32)
100% 1940
15.0 IPS
 
Depth Estimation (F16)
100% 1987
15.4 IPS
 
Depth Estimation (I8)
95% 4531
35.1 IPS
 
Style Transfer (F32)
100% 3072
4.04 IPS
 
Style Transfer (F16)
100% 3074
4.04 IPS
 
Style Transfer (I8)
98% 7952
10.5 IPS
 
Image Super-Resolution (F32)
100% 1286
45.9 IPS
 
Image Super-Resolution (F16)
100% 1233
44.0 IPS
 
Image Super-Resolution (I8)
98% 3346
119.5 IPS
 
Text Classification (F32)
100% 388
557.4 IPS
 
Text Classification (F16)
100% 486
698.8 IPS
 
Text Classification (I8)
92% 687
986.7 IPS
 
Machine Translation (F32)
100% 895
16.5 IPS
 
Machine Translation (F16)
100% 828
15.2 IPS
 
Machine Translation (I8)
64% 770
14.2 IPS
 

Compare

Set Baseline Geekbench 6 now available