Geekbench ML Score

348
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date February 23 2024 01:20 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 2312FPCA6G
Model IDXiaomi 2312FPCA6G
Motherboard emerald
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 11.39 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 169
31.6 IPS
 
Image Classification (F16)
100% 155
29.0 IPS
 
Image Classification (I8)
97% 260
48.7 IPS
 
Image Segmentation (F32)
100% 234
3.90 IPS
 
Image Segmentation (F16)
100% 238
3.98 IPS
 
Image Segmentation (I8)
98% 343
5.73 IPS
 
Pose Estimation (F32)
100% 362
0.44 IPS
 
Pose Estimation (F16)
100% 355
0.43 IPS
 
Pose Estimation (I8)
100% 1533
1.86 IPS
 
Object Detection (F32)
100% 185
13.8 IPS
 
Object Detection (F16)
100% 204
15.2 IPS
 
Object Detection (I8)
61% 327
24.4 IPS
 
Face Detection (F32)
100% 393
4.67 IPS
 
Face Detection (F16)
100% 396
4.71 IPS
 
Face Detection (I8)
86% 744
8.85 IPS
 
Depth Estimation (F32)
100% 384
2.98 IPS
 
Depth Estimation (F16)
100% 391
3.03 IPS
 
Depth Estimation (I8)
95% 762
5.91 IPS
 
Style Transfer (F32)
100% 628
0.83 IPS
 
Style Transfer (F16)
100% 608
0.80 IPS
 
Style Transfer (I8)
98% 1784
2.35 IPS
 
Image Super-Resolution (F32)
100% 228
8.14 IPS
 
Image Super-Resolution (F16)
100% 206
7.34 IPS
 
Image Super-Resolution (I8)
98% 636
22.7 IPS
 
Text Classification (F32)
100% 187
268.2 IPS
 
Text Classification (F16)
100% 189
271.3 IPS
 
Text Classification (I8)
92% 155
223.1 IPS
 
Machine Translation (F32)
100% 421
7.74 IPS
 
Machine Translation (F16)
100% 396
7.30 IPS
 
Machine Translation (I8)
64% 237
4.36 IPS
 

Compare

Set Baseline Geekbench 6 now available