Geekbench ML Score

652
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 09 2025 02:16 PM
Views 2

System Information

System Information
Operating System Android 15
Model samsung SM-X216B
Model IDsamsung SM-X216B
Motherboard holi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 3.29 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 436
46.7 IPS
 
Image Classification (F16)
100% 712
76.3 IPS
 
Image Classification (I8)
80% 664
71.1 IPS
 
Image Segmentation (F32)
100% 911
5.63 IPS
 
Image Segmentation (F16)
100% 1508
9.31 IPS
 
Image Segmentation (I8)
89% 1563
9.66 IPS
 
Pose Estimation (F32)
100% 431
1.75 IPS
 
Pose Estimation (F16)
100% 779
3.15 IPS
 
Pose Estimation (I8)
80% 776
3.14 IPS
 
Object Detection (F32)
100% 373
13.1 IPS
 
Object Detection (F16)
99% 513
18.0 IPS
 
Object Detection (I8)
53% 488
17.1 IPS
 
Face Detection (F32)
100% 805
9.25 IPS
 
Face Detection (F16)
97% 1433
16.5 IPS
 
Face Detection (I8)
75% 1309
15.0 IPS
 
Text Classification (F32)
100% 410
162.0 IPS
 
Text Classification (F16)
98% 527
208.6 IPS
 
Machine Translation (F32)
100% 292
45.0 IPS
 
Machine Translation (F16)
100% 289
44.6 IPS
 

Compare

Set Baseline Geekbench 6 now available