Geekbench ML Score

1070
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 16 2025 08:36 PM
Views 3

System Information

System Information
Operating System Android 14
Model samsung SM-X716B
Model IDsamsung SM-X716B
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 @ 3.36 GHz
Memory Information
Size 10.91 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 656
122.8 IPS
 
Image Classification (F16)
100% 921
172.4 IPS
 
Image Classification (I8)
99% 682
127.6 IPS
 
Image Segmentation (F32)
100% 842
14.1 IPS
 
Image Segmentation (F16)
100% 1150
19.2 IPS
 
Image Segmentation (I8)
98% 946
15.8 IPS
 
Pose Estimation (F32)
100% 970
1.17 IPS
 
Pose Estimation (F16)
100% 1392
1.69 IPS
 
Pose Estimation (I8)
100% 1389
1.68 IPS
 
Object Detection (F32)
100% 269
20.1 IPS
 
Object Detection (F16)
100% 394
29.4 IPS
 
Object Detection (I8)
62% 406
30.3 IPS
 
Face Detection (F32)
100% 2242
26.7 IPS
 
Face Detection (F16)
97% 3030
36.0 IPS
 
Face Detection (I8)
86% 2883
34.3 IPS
 
Depth Estimation (F32)
100% 1500
11.6 IPS
 
Depth Estimation (F16)
100% 2946
22.8 IPS
 
Depth Estimation (I8)
95% 2856
22.1 IPS
 
Style Transfer (F32)
100% 3788
4.98 IPS
 
Style Transfer (F16)
100% 8562
11.3 IPS
 
Style Transfer (I8)
98% 8532
11.2 IPS
 
Image Super-Resolution (F32)
100% 456
16.3 IPS
 
Image Super-Resolution (F16)
100% 392
14.0 IPS
 
Image Super-Resolution (I8)
98% 392
14.0 IPS
 
Text Classification (F32)
100% 462
664.4 IPS
 
Text Classification (F16)
100% 460
661.0 IPS
 
Text Classification (I8)
92% 684
982.3 IPS
 
Machine Translation (F32)
100% 710
13.1 IPS
 
Machine Translation (F16)
100% 691
12.7 IPS
 
Machine Translation (I8)
64% 747
13.7 IPS
 

Compare

Set Baseline Geekbench 6 now available