Geekbench ML Score

175
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 06 2025 11:22 AM
Views 2

System Information

System Information
Operating System Android 14
Model Vocal Vocal V2
Model IDVocal Vocal V2
Motherboard V2
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 5.61 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 92
17.2 IPS
 
Image Classification (F16)
100% 165
30.9 IPS
 
Image Classification (I8)
97% 154
28.8 IPS
 
Image Segmentation (F32)
100% 116
1.94 IPS
 
Image Segmentation (F16)
100% 183
3.06 IPS
 
Image Segmentation (I8)
98% 186
3.10 IPS
 
Pose Estimation (F32)
100% 89
0.11 IPS
 
Pose Estimation (F16)
100% 105
0.13 IPS
 
Pose Estimation (I8)
100% 105
0.13 IPS
 
Object Detection (F32)
100% 62
4.60 IPS
 
Object Detection (F16)
100% 116
8.69 IPS
 
Object Detection (I8)
62% 102
7.63 IPS
 
Face Detection (F32)
100% 227
2.69 IPS
 
Face Detection (F16)
98% 361
4.30 IPS
 
Face Detection (I8)
86% 342
4.06 IPS
 
Depth Estimation (F32)
100% 170
1.32 IPS
 
Depth Estimation (F16)
100% 227
1.76 IPS
 
Depth Estimation (I8)
95% 221
1.72 IPS
 
Style Transfer (F32)
100% 344
0.45 IPS
 
Style Transfer (F16)
100% 478
0.63 IPS
 
Style Transfer (I8)
98% 478
0.63 IPS
 
Image Super-Resolution (F32)
100% 92
3.28 IPS
 
Image Super-Resolution (F16)
100% 141
5.04 IPS
 
Image Super-Resolution (I8)
98% 140
5.01 IPS
 
Text Classification (F32)
100% 146
209.2 IPS
 
Text Classification (F16)
100% 146
209.4 IPS
 
Text Classification (I8)
92% 236
339.4 IPS
 
Machine Translation (F32)
100% 269
4.94 IPS
 
Machine Translation (F16)
100% 268
4.93 IPS
 
Machine Translation (I8)
64% 244
4.49 IPS
 

Compare

Set Baseline Geekbench 6 now available