Geekbench ML Score

2304
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date November 08 2024 04:45 PM
Views 1

System Information

System Information
Operating System Android 15
Model asus ASUSAI2501E
Model IDasus ASUSAI2501E
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 22.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1375
257.3 IPS
 
Image Classification (F16)
100% 1384
259.0 IPS
 
Image Classification (I8)
97% 1892
354.0 IPS
 
Image Segmentation (F32)
100% 1835
30.6 IPS
 
Image Segmentation (F16)
100% 1830
30.6 IPS
 
Image Segmentation (I8)
98% 2088
34.9 IPS
 
Pose Estimation (F32)
100% 2354
2.85 IPS
 
Pose Estimation (F16)
100% 2301
2.79 IPS
 
Pose Estimation (I8)
100% 9662
11.7 IPS
 
Object Detection (F32)
100% 1327
99.0 IPS
 
Object Detection (F16)
100% 1326
99.0 IPS
 
Object Detection (I8)
61% 2517
187.9 IPS
 
Face Detection (F32)
100% 2754
32.7 IPS
 
Face Detection (F16)
100% 2702
32.1 IPS
 
Face Detection (I8)
86% 4653
55.3 IPS
 
Depth Estimation (F32)
100% 2521
19.6 IPS
 
Depth Estimation (F16)
100% 2503
19.4 IPS
 
Depth Estimation (I8)
95% 4783
37.1 IPS
 
Style Transfer (F32)
100% 3761
4.95 IPS
 
Style Transfer (F16)
100% 3725
4.90 IPS
 
Style Transfer (I8)
98% 10698
14.1 IPS
 
Image Super-Resolution (F32)
100% 1502
53.6 IPS
 
Image Super-Resolution (F16)
100% 1509
53.9 IPS
 
Image Super-Resolution (I8)
98% 4860
173.6 IPS
 
Text Classification (F32)
100% 1198
1.72 KIPS
 
Text Classification (F16)
100% 1197
1.72 KIPS
 
Text Classification (I8)
92% 842
1.21 KIPS
 
Machine Translation (F32)
100% 2312
42.5 IPS
 
Machine Translation (F16)
100% 2274
41.8 IPS
 
Machine Translation (I8)
64% 1170
21.5 IPS
 

Compare

Set Baseline Geekbench 6 now available