Geekbench ML Score

2294
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date November 08 2024 04:40 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% 1404
262.6 IPS
 
Image Classification (F16)
100% 1352
253.0 IPS
 
Image Classification (I8)
97% 1863
348.6 IPS
 
Image Segmentation (F32)
100% 1825
30.5 IPS
 
Image Segmentation (F16)
100% 1825
30.5 IPS
 
Image Segmentation (I8)
98% 1939
32.4 IPS
 
Pose Estimation (F32)
100% 2350
2.85 IPS
 
Pose Estimation (F16)
100% 2287
2.77 IPS
 
Pose Estimation (I8)
100% 9666
11.7 IPS
 
Object Detection (F32)
100% 1332
99.5 IPS
 
Object Detection (F16)
100% 1329
99.2 IPS
 
Object Detection (I8)
61% 2374
177.2 IPS
 
Face Detection (F32)
100% 2783
33.1 IPS
 
Face Detection (F16)
100% 2717
32.3 IPS
 
Face Detection (I8)
86% 4616
54.9 IPS
 
Depth Estimation (F32)
100% 2521
19.6 IPS
 
Depth Estimation (F16)
100% 2499
19.4 IPS
 
Depth Estimation (I8)
95% 4795
37.2 IPS
 
Style Transfer (F32)
100% 3755
4.94 IPS
 
Style Transfer (F16)
100% 3726
4.90 IPS
 
Style Transfer (I8)
98% 10622
14.0 IPS
 
Image Super-Resolution (F32)
100% 1484
53.0 IPS
 
Image Super-Resolution (F16)
100% 1512
54.0 IPS
 
Image Super-Resolution (I8)
98% 4976
177.7 IPS
 
Text Classification (F32)
100% 1196
1.72 KIPS
 
Text Classification (F16)
100% 1175
1.69 KIPS
 
Text Classification (I8)
92% 878
1.26 KIPS
 
Machine Translation (F32)
100% 2284
42.0 IPS
 
Machine Translation (F16)
100% 2249
41.4 IPS
 
Machine Translation (I8)
64% 1189
21.9 IPS
 

Compare

Set Baseline Geekbench 6 now available