Geekbench ML Score

864
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date August 23 2024 05:48 AM
Views 2

System Information

System Information
Operating System Android 14
Model Xiaomi Redmi K60 Pro
Model IDXiaomi 22127RK46C
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 10.93 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 546
102.2 IPS
 
Image Classification (F16)
100% 854
159.8 IPS
 
Image Classification (I8)
99% 937
175.4 IPS
 
Image Segmentation (F32)
100% 861
14.4 IPS
 
Image Segmentation (F16)
100% 972
16.2 IPS
 
Image Segmentation (I8)
98% 936
15.6 IPS
 
Pose Estimation (F32)
100% 759
0.92 IPS
 
Pose Estimation (F16)
100% 1200
1.45 IPS
 
Pose Estimation (I8)
100% 1227
1.49 IPS
 
Object Detection (F32)
100% 238
17.8 IPS
 
Object Detection (F16)
100% 256
19.1 IPS
 
Object Detection (I8)
62% 280
20.9 IPS
 
Face Detection (F32)
100% 1983
23.6 IPS
 
Face Detection (F16)
97% 2930
34.8 IPS
 
Face Detection (I8)
86% 2680
31.9 IPS
 
Depth Estimation (F32)
100% 1251
9.70 IPS
 
Depth Estimation (F16)
100% 2353
18.3 IPS
 
Depth Estimation (I8)
95% 2524
19.6 IPS
 
Style Transfer (F32)
100% 3119
4.10 IPS
 
Style Transfer (F16)
100% 7228
9.51 IPS
 
Style Transfer (I8)
98% 7264
9.56 IPS
 
Image Super-Resolution (F32)
100% 397
14.2 IPS
 
Image Super-Resolution (F16)
100% 232
8.28 IPS
 
Image Super-Resolution (I8)
98% 230
8.21 IPS
 
Text Classification (F32)
100% 293
420.8 IPS
 
Text Classification (F16)
100% 291
418.5 IPS
 
Text Classification (I8)
92% 425
610.1 IPS
 
Machine Translation (F32)
100% 517
9.51 IPS
 
Machine Translation (F16)
100% 517
9.51 IPS
 
Machine Translation (I8)
64% 502
9.24 IPS
 

Compare

Set Baseline Geekbench 6 now available