Upload Date | August 29 2025 10:16 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 8 Elite |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S25+ |
Model ID | samsung SM-S936B |
Motherboard | sun |
Governor | walt |
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 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
445
82.8 IPS |
|
Image Classification (HP)
|
100% |
21007
3.91 KIPS |
|
Image Classification (Q)
|
97% |
49505
9.24 KIPS |
|
Image Segmentation (SP)
|
100% |
569
9.22 IPS |
|
Image Segmentation (HP)
|
100% |
13757
223.0 IPS |
|
Image Segmentation (Q)
|
98% |
42301
687.8 IPS |
|
Pose Estimation (SP)
|
100% |
675
0.79 IPS |
|
Pose Estimation (HP)
|
100% |
122461
142.9 IPS |
|
Pose Estimation (Q)
|
98% |
475302
556.3 IPS |
|
Object Detection (SP)
|
100% |
238
18.9 IPS |
|
Object Detection (HP)
|
100% |
18058
1.43 KIPS |
|
Object Detection (Q)
|
85% |
20512
1.65 KIPS |
|
Face Detection (SP)
|
100% |
564
6.70 IPS |
|
Face Detection (HP)
|
100% |
38239
454.4 IPS |
|
Face Detection (Q)
|
97% |
131943
1.57 KIPS |
|
Depth Estimation (SP)
|
100% |
665
5.13 IPS |
|
Depth Estimation (HP)
|
99% |
83630
644.3 IPS |
|
Depth Estimation (Q)
|
63% |
142988
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
1076
1.38 IPS |
|
Style Transfer (HP)
|
98% |
98566
127.1 IPS |
|
Style Transfer (Q)
|
98% |
489968
631.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
291
10.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
53246
1.97 KIPS |
|
Image Super-Resolution (Q)
|
97% |
132474
4.91 KIPS |
|
Text Classification (SP)
|
100% |
394
526.0 IPS |
|
Text Classification (HP)
|
100% |
3906
5.21 KIPS |
|
Text Classification (Q)
|
93% |
7955
10.7 KIPS |
|
Machine Translation (SP)
|
100% |
736
12.7 IPS |
|
Machine Translation (HP)
|
100% |
4577
78.8 IPS |
|
Machine Translation (Q)
|
56% |
3030
78.0 IPS |