| Upload Date | October 29 2025 01:44 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm Snapdragon 8 Elite |
| System Information | |
|---|---|
| Operating System | Android 16 |
| 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 | 10.85 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1948
362.3 IPS |
|
|
Image Classification (HP)
|
100% |
1866
347.0 IPS |
|
|
Image Classification (Q)
|
100% |
4331
805.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
2262
36.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2350
38.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
5239
85.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
5005
5.84 IPS |
|
|
Pose Estimation (HP)
|
100% |
5088
5.94 IPS |
|
|
Pose Estimation (Q)
|
84% |
12748
15.1 IPS |
|
|
Object Detection (SP)
|
98% |
1640
130.5 IPS |
|
|
Object Detection (HP)
|
98% |
1568
124.8 IPS |
|
|
Object Detection (Q)
|
83% |
3211
259.4 IPS |
|
|
Face Detection (SP)
|
100% |
3646
43.3 IPS |
|
|
Face Detection (HP)
|
100% |
3907
46.4 IPS |
|
|
Face Detection (Q)
|
95% |
7496
89.5 IPS |
|
|
Depth Estimation (SP)
|
99% |
3644
28.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
4243
32.8 IPS |
|
|
Depth Estimation (Q)
|
64% |
8753
80.2 IPS |
|
|
Style Transfer (SP)
|
89% |
11159
14.5 IPS |
|
|
Style Transfer (HP)
|
89% |
11380
14.8 IPS |
|
|
Style Transfer (Q)
|
98% |
23852
30.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1867
68.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1670
61.7 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
3285
121.7 IPS |
|
|
Text Classification (SP)
|
100% |
790
1.05 KIPS |
|
|
Text Classification (HP)
|
99% |
697
930.6 IPS |
|
|
Text Classification (Q)
|
88% |
589
794.2 IPS |
|
|
Machine Translation (SP)
|
100% |
1341
23.1 IPS |
|
|
Machine Translation (HP)
|
100% |
1295
22.3 IPS |
|
|
Machine Translation (Q)
|
50% |
454
16.1 IPS |