Geekbench AI Score

512
Single Precision Score
20969
Half Precision Score
51691
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 31 2024 02:35 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model nubia NX721J
Model IDnubia NX721J
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.30 GHz
Memory Information
Size 11.01 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 322
59.9 IPS
 
Image Classification (HP)
100% 16425
3.05 KIPS
 
Image Classification (Q)
97% 42609
7.95 KIPS
 
Image Segmentation (SP)
100% 403
6.54 IPS
 
Image Segmentation (HP)
100% 10849
175.9 IPS
 
Image Segmentation (Q)
98% 31459
511.5 IPS
 
Pose Estimation (SP)
100% 544
0.64 IPS
 
Pose Estimation (HP)
100% 77046
89.9 IPS
 
Pose Estimation (Q)
98% 398581
466.5 IPS
 
Object Detection (SP)
100% 307
24.4 IPS
 
Object Detection (HP)
100% 14901
1.18 KIPS
 
Object Detection (Q)
86% 20426
1.64 KIPS
 
Face Detection (SP)
100% 754
8.95 IPS
 
Face Detection (HP)
100% 33199
394.5 IPS
 
Face Detection (Q)
97% 128780
1.54 KIPS
 
Depth Estimation (SP)
100% 656
5.06 IPS
 
Depth Estimation (HP)
99% 58914
453.9 IPS
 
Depth Estimation (Q)
63% 117734
1.10 KIPS
 
Style Transfer (SP)
100% 1051
1.35 IPS
 
Style Transfer (HP)
98% 82467
106.3 IPS
 
Style Transfer (Q)
98% 421954
544.1 IPS
 
Image Super-Resolution (SP)
100% 348
12.9 IPS
 
Image Super-Resolution (HP)
100% 40626
1.50 KIPS
 
Image Super-Resolution (Q)
97% 104555
3.87 KIPS
 
Text Classification (SP)
100% 446
595.1 IPS
 
Text Classification (HP)
100% 3234
4.32 KIPS
 
Text Classification (Q)
93% 7004
9.40 KIPS
 
Machine Translation (SP)
100% 715
12.3 IPS
 
Machine Translation (HP)
100% 3792
65.3 IPS
 
Machine Translation (Q)
55% 2664
69.8 IPS
 

Compare

Set Baseline Geekbench 6 now available