Geekbench ML Score

438
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date March 09 2025 11:49 AM
Views 5

System Information

System Information
Operating System Android 10
Model HUAWEI LIO-N29
Model IDHUAWEI LIO-N29
Motherboard LIO
CPU Information
Name vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 3 part 3392 revision 1
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 22 Cores @ 2.36 GHz
Cluster 32 Cores @ 2.86 GHz
Memory Information
Size 7.25 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 358
38.3 IPS
 
Image Classification (F16)
100% 359
38.5 IPS
 
Image Classification (I8)
81% 241
25.8 IPS
 
Image Segmentation (F32)
100% 534
3.30 IPS
 
Image Segmentation (F16)
100% 536
3.31 IPS
 
Image Segmentation (I8)
89% 3938
24.3 IPS
 
Pose Estimation (F32)
100% 231
0.93 IPS
 
Pose Estimation (F16)
100% 228
0.92 IPS
 
Pose Estimation (I8)
80% 73
0.30 IPS
 
Object Detection (F32)
100% 534
18.7 IPS
 
Object Detection (F16)
100% 3096
108.7 IPS
 
Object Detection (I8)
52% 344
12.1 IPS
 
Face Detection (F32)
100% 517
5.94 IPS
 
Face Detection (F16)
100% 527
6.06 IPS
 
Face Detection (I8)
75% 342
3.93 IPS
 
Text Classification (F32)
100% 587
232.0 IPS
 
Text Classification (F16)
100% 178
70.5 IPS
 
Machine Translation (F32)
100% 460
70.9 IPS
 
Machine Translation (F16)
100% 459
70.7 IPS
 

Compare

Set Baseline Geekbench 6 now available