Geekbench ML Score

2381
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 19 2024 09:01 AM
Views 1

System Information

System Information
Operating System Android 14
Model Qualcomm msmnile_gvmq for arm64
Model IDQualcomm msmnile_gvmq for arm64
Motherboard msmnile
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3403 revision 0
Base Frequency 2.59 GHz
Cluster 14 Cores @ 2.25 GHz
Cluster 24 Cores @ 2.59 GHz
Memory Information
Size 10.20 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
33% 2341
250.8 IPS
 
Image Classification (F16)
3% 2829
303.1 IPS
 
Image Classification (I8)
3% 2825
302.7 IPS
 
Image Segmentation (F32)
100% 5483
33.9 IPS
 
Image Segmentation (F16)
100% 9167
56.6 IPS
 
Image Segmentation (I8)
89% 9388
58.0 IPS
 
Pose Estimation (F32)
27% 2717
11.0 IPS
 
Pose Estimation (F16)
47% 5207
21.1 IPS
 
Pose Estimation (I8)
0% 5176
20.9 IPS
 
Object Detection (F32)
79% 925
32.5 IPS
 
Object Detection (F16)
84% 1068
37.5 IPS
 
Object Detection (I8)
39% 1066
37.4 IPS
 
Face Detection (F32)
57% 3264
37.5 IPS
 
Face Detection (F16)
46% 5548
63.7 IPS
 
Face Detection (I8)
41% 5121
58.8 IPS
 
Text Classification (F32)
48% 642
253.9 IPS
 
Text Classification (F16)
46% 735
290.8 IPS
 
Machine Translation (F32)
100% 694
106.9 IPS
 
Machine Translation (F16)
100% 702
108.1 IPS
 

Compare

Set Baseline Geekbench 6 now available