Geekbench ML Score

349
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 06 2024 06:17 PM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-A146U
Model IDsamsung SM-A146U
Motherboard a14xm
CPU Information
Name ARM MT6833V/NZA
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 3.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 229
42.8 IPS
 
Image Classification (F16)
100% 185
34.6 IPS
 
Image Classification (I8)
97% 388
72.6 IPS
 
Image Segmentation (F32)
100% 256
4.28 IPS
 
Image Segmentation (F16)
100% 244
4.08 IPS
 
Image Segmentation (I8)
98% 420
7.01 IPS
 
Pose Estimation (F32)
100% 322
0.39 IPS
 
Pose Estimation (F16)
100% 269
0.33 IPS
 
Pose Estimation (I8)
100% 1098
1.33 IPS
 
Object Detection (F32)
100% 120
8.98 IPS
 
Object Detection (F16)
100% 159
11.9 IPS
 
Object Detection (I8)
61% 486
36.3 IPS
 
Face Detection (F32)
100% 375
4.45 IPS
 
Face Detection (F16)
100% 330
3.93 IPS
 
Face Detection (I8)
86% 827
9.83 IPS
 
Depth Estimation (F32)
100% 362
2.81 IPS
 
Depth Estimation (F16)
100% 296
2.30 IPS
 
Depth Estimation (I8)
95% 773
5.99 IPS
 
Style Transfer (F32)
100% 429
0.56 IPS
 
Style Transfer (F16)
100% 468
0.62 IPS
 
Style Transfer (I8)
98% 1303
1.71 IPS
 
Image Super-Resolution (F32)
100% 181
6.48 IPS
 
Image Super-Resolution (F16)
100% 184
6.57 IPS
 
Image Super-Resolution (I8)
98% 652
23.3 IPS
 
Text Classification (F32)
100% 311
446.7 IPS
 
Text Classification (F16)
100% 301
433.3 IPS
 
Text Classification (I8)
92% 251
361.2 IPS
 
Machine Translation (F32)
100% 352
6.48 IPS
 
Machine Translation (F16)
100% 377
6.93 IPS
 
Machine Translation (I8)
64% 356
6.56 IPS
 

Compare

Set Baseline Geekbench 6 now available