| Upload Date | November 07 2025 12:30 AM |
| Views | 2 |
| 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% |
2032
377.8 IPS |
|
|
Image Classification (HP)
|
100% |
1893
352.1 IPS |
|
|
Image Classification (Q)
|
100% |
4437
825.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
2383
38.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2382
38.6 IPS |
|
|
Image Segmentation (Q)
|
98% |
5225
85.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
5457
6.37 IPS |
|
|
Pose Estimation (HP)
|
100% |
5426
6.33 IPS |
|
|
Pose Estimation (Q)
|
84% |
13141
15.6 IPS |
|
|
Object Detection (SP)
|
98% |
1712
136.3 IPS |
|
|
Object Detection (HP)
|
98% |
1689
134.4 IPS |
|
|
Object Detection (Q)
|
83% |
3986
322.0 IPS |
|
|
Face Detection (SP)
|
100% |
4488
53.3 IPS |
|
|
Face Detection (HP)
|
100% |
4543
54.0 IPS |
|
|
Face Detection (Q)
|
95% |
9745
116.3 IPS |
|
|
Depth Estimation (SP)
|
99% |
4533
35.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4453
34.4 IPS |
|
|
Depth Estimation (Q)
|
64% |
10520
96.4 IPS |
|
|
Style Transfer (SP)
|
89% |
11846
15.4 IPS |
|
|
Style Transfer (HP)
|
89% |
11618
15.1 IPS |
|
|
Style Transfer (Q)
|
98% |
23090
29.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2051
75.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2281
84.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
5238
194.1 IPS |
|
|
Text Classification (SP)
|
100% |
810
1.08 KIPS |
|
|
Text Classification (HP)
|
99% |
785
1.05 KIPS |
|
|
Text Classification (Q)
|
88% |
1026
1.38 KIPS |
|
|
Machine Translation (SP)
|
100% |
1345
23.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1362
23.5 IPS |
|
|
Machine Translation (Q)
|
50% |
562
19.9 IPS |