Geekbench ML Score

211
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date March 19 2025 11:45 AM
Views 9

System Information

System Information
Operating System Android 13
Model alps TX205
Model IDalps TX205
Motherboard tb8781p1_64
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 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 80
15.0 IPS
 
Image Classification (F16)
100% 79
14.8 IPS
 
Image Classification (I8)
97% 126
23.7 IPS
 
Image Segmentation (F32)
100% 188
3.14 IPS
 
Image Segmentation (F16)
100% 191
3.18 IPS
 
Image Segmentation (I8)
98% 273
4.57 IPS
 
Pose Estimation (F32)
100% 293
0.36 IPS
 
Pose Estimation (F16)
100% 282
0.34 IPS
 
Pose Estimation (I8)
100% 1334
1.62 IPS
 
Object Detection (F32)
100% 104
7.76 IPS
 
Object Detection (F16)
100% 108
8.05 IPS
 
Object Detection (I8)
61% 173
12.9 IPS
 
Face Detection (F32)
100% 273
3.25 IPS
 
Face Detection (F16)
100% 275
3.27 IPS
 
Face Detection (I8)
86% 500
5.95 IPS
 
Depth Estimation (F32)
100% 261
2.02 IPS
 
Depth Estimation (F16)
100% 268
2.08 IPS
 
Depth Estimation (I8)
95% 551
4.27 IPS
 
Style Transfer (F32)
100% 550
0.72 IPS
 
Style Transfer (F16)
100% 547
0.72 IPS
 
Style Transfer (I8)
98% 1742
2.29 IPS
 
Image Super-Resolution (F32)
100% 154
5.51 IPS
 
Image Super-Resolution (F16)
100% 154
5.49 IPS
 
Image Super-Resolution (I8)
98% 410
14.6 IPS
 
Text Classification (F32)
100% 60
86.4 IPS
 
Text Classification (F16)
100% 62
89.0 IPS
 
Text Classification (I8)
92% 60
86.6 IPS
 
Machine Translation (F32)
100% 140
2.58 IPS
 
Machine Translation (F16)
100% 131
2.41 IPS
 
Machine Translation (I8)
64% 112
2.05 IPS
 

Compare

Set Baseline Geekbench 6 now available