Geekbench ML Score

606
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 10 2025 09:21 AM
Views 3

System Information

System Information
Operating System Android 15
Model vivo V2408A
Model IDvivo V2408A
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.32 GHz
Memory Information
Size 14.76 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 262
49.1 IPS
 
Image Classification (F16)
100% 262
49.1 IPS
 
Image Classification (I8)
97% 670
125.3 IPS
 
Image Segmentation (F32)
100% 338
5.64 IPS
 
Image Segmentation (F16)
100% 338
5.65 IPS
 
Image Segmentation (I8)
98% 650
10.9 IPS
 
Pose Estimation (F32)
100% 468
0.57 IPS
 
Pose Estimation (F16)
100% 471
0.57 IPS
 
Pose Estimation (I8)
100% 1781
2.16 IPS
 
Object Detection (F32)
100% 269
20.1 IPS
 
Object Detection (F16)
100% 267
20.0 IPS
 
Object Detection (I8)
61% 738
55.1 IPS
 
Face Detection (F32)
100% 695
8.26 IPS
 
Face Detection (F16)
100% 693
8.23 IPS
 
Face Detection (I8)
86% 1573
18.7 IPS
 
Depth Estimation (F32)
100% 609
4.72 IPS
 
Depth Estimation (F16)
100% 608
4.72 IPS
 
Depth Estimation (I8)
95% 1649
12.8 IPS
 
Style Transfer (F32)
100% 1080
1.42 IPS
 
Style Transfer (F16)
100% 1079
1.42 IPS
 
Style Transfer (I8)
98% 2834
3.73 IPS
 
Image Super-Resolution (F32)
100% 322
11.5 IPS
 
Image Super-Resolution (F16)
100% 322
11.5 IPS
 
Image Super-Resolution (I8)
98% 1149
41.1 IPS
 
Text Classification (F32)
100% 370
531.1 IPS
 
Text Classification (F16)
100% 369
530.3 IPS
 
Text Classification (I8)
92% 577
829.0 IPS
 
Machine Translation (F32)
100% 671
12.3 IPS
 
Machine Translation (F16)
100% 668
12.3 IPS
 
Machine Translation (I8)
64% 682
12.5 IPS
 

Compare

Set Baseline Geekbench 6 now available