Upload Date | July 15 2025 12:44 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 8 Elite |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S25 Ultra |
Model ID | samsung SM-S938B |
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% |
413
76.9 IPS |
|
Image Classification (HP)
|
100% |
21411
3.98 KIPS |
|
Image Classification (Q)
|
97% |
48952
9.14 KIPS |
|
Image Segmentation (SP)
|
100% |
472
7.65 IPS |
|
Image Segmentation (HP)
|
100% |
13554
219.7 IPS |
|
Image Segmentation (Q)
|
98% |
41707
678.2 IPS |
|
Pose Estimation (SP)
|
100% |
568
0.66 IPS |
|
Pose Estimation (HP)
|
100% |
118615
138.4 IPS |
|
Pose Estimation (Q)
|
98% |
476606
557.8 IPS |
|
Object Detection (SP)
|
100% |
274
21.7 IPS |
|
Object Detection (HP)
|
100% |
17090
1.36 KIPS |
|
Object Detection (Q)
|
85% |
19787
1.59 KIPS |
|
Face Detection (SP)
|
100% |
484
5.75 IPS |
|
Face Detection (HP)
|
100% |
33776
401.3 IPS |
|
Face Detection (Q)
|
97% |
101944
1.22 KIPS |
|
Depth Estimation (SP)
|
100% |
427
3.29 IPS |
|
Depth Estimation (HP)
|
99% |
79706
614.1 IPS |
|
Depth Estimation (Q)
|
63% |
132439
1.23 KIPS |
|
Style Transfer (SP)
|
100% |
891
1.15 IPS |
|
Style Transfer (HP)
|
98% |
98257
126.7 IPS |
|
Style Transfer (Q)
|
98% |
488990
630.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
220
8.14 IPS |
|
Image Super-Resolution (HP)
|
100% |
51519
1.90 KIPS |
|
Image Super-Resolution (Q)
|
97% |
128569
4.76 KIPS |
|
Text Classification (SP)
|
100% |
272
363.5 IPS |
|
Text Classification (HP)
|
100% |
3838
5.12 KIPS |
|
Text Classification (Q)
|
93% |
7639
10.3 KIPS |
|
Machine Translation (SP)
|
100% |
471
8.11 IPS |
|
Machine Translation (HP)
|
100% |
3730
64.3 IPS |
|
Machine Translation (Q)
|
56% |
2629
67.7 IPS |