Geekbench ML Score

518
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 03 2025 02:12 AM
Views 1

System Information

System Information
Operating System Android 14
Model alps k6878v1_64_ssdev
Model IDalps k6878v1_64_ssdev
Motherboard k6878v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.50 GHz
Memory Information
Size 7.20 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 254
47.6 IPS
 
Image Classification (F16)
100% 253
47.4 IPS
 
Image Classification (I8)
97% 475
88.9 IPS
 
Image Segmentation (F32)
100% 351
5.86 IPS
 
Image Segmentation (F16)
100% 342
5.72 IPS
 
Image Segmentation (I8)
98% 547
9.14 IPS
 
Pose Estimation (F32)
100% 536
0.65 IPS
 
Pose Estimation (F16)
100% 533
0.64 IPS
 
Pose Estimation (I8)
100% 2272
2.75 IPS
 
Object Detection (F32)
100% 264
19.7 IPS
 
Object Detection (F16)
100% 268
20.0 IPS
 
Object Detection (I8)
61% 497
37.1 IPS
 
Face Detection (F32)
100% 516
6.13 IPS
 
Face Detection (F16)
100% 523
6.21 IPS
 
Face Detection (I8)
86% 1139
13.5 IPS
 
Depth Estimation (F32)
100% 540
4.19 IPS
 
Depth Estimation (F16)
100% 540
4.19 IPS
 
Depth Estimation (I8)
95% 1188
9.21 IPS
 
Style Transfer (F32)
100% 872
1.15 IPS
 
Style Transfer (F16)
100% 870
1.14 IPS
 
Style Transfer (I8)
98% 2597
3.42 IPS
 
Image Super-Resolution (F32)
100% 313
11.2 IPS
 
Image Super-Resolution (F16)
100% 311
11.1 IPS
 
Image Super-Resolution (I8)
98% 1036
37.0 IPS
 
Text Classification (F32)
100% 347
498.7 IPS
 
Text Classification (F16)
100% 348
500.1 IPS
 
Text Classification (I8)
92% 327
470.3 IPS
 
Machine Translation (F32)
100% 506
9.31 IPS
 
Machine Translation (F16)
100% 518
9.53 IPS
 
Machine Translation (I8)
64% 273
5.02 IPS
 

Compare

Set Baseline Geekbench 6 now available