| Upload Date | November 10 2025 08:13 AM |
| 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% |
1942
361.2 IPS |
|
|
Image Classification (HP)
|
100% |
2035
378.5 IPS |
|
|
Image Classification (Q)
|
100% |
4468
830.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
2317
37.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2412
39.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
5121
83.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
5429
6.33 IPS |
|
|
Pose Estimation (HP)
|
100% |
5268
6.15 IPS |
|
|
Pose Estimation (Q)
|
84% |
12701
15.1 IPS |
|
|
Object Detection (SP)
|
98% |
1629
129.6 IPS |
|
|
Object Detection (HP)
|
98% |
1658
132.0 IPS |
|
|
Object Detection (Q)
|
83% |
3912
316.0 IPS |
|
|
Face Detection (SP)
|
100% |
4175
49.6 IPS |
|
|
Face Detection (HP)
|
100% |
4241
50.4 IPS |
|
|
Face Detection (Q)
|
95% |
8626
103.0 IPS |
|
|
Depth Estimation (SP)
|
99% |
4404
34.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4370
33.8 IPS |
|
|
Depth Estimation (Q)
|
64% |
10451
95.7 IPS |
|
|
Style Transfer (SP)
|
89% |
11242
14.6 IPS |
|
|
Style Transfer (HP)
|
89% |
11277
14.6 IPS |
|
|
Style Transfer (Q)
|
98% |
25554
33.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2181
80.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2143
79.1 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
4666
172.9 IPS |
|
|
Text Classification (SP)
|
100% |
801
1.07 KIPS |
|
|
Text Classification (HP)
|
99% |
746
996.3 IPS |
|
|
Text Classification (Q)
|
88% |
694
936.4 IPS |
|
|
Machine Translation (SP)
|
100% |
1320
22.7 IPS |
|
|
Machine Translation (HP)
|
100% |
1324
22.8 IPS |
|
|
Machine Translation (Q)
|
50% |
553
19.6 IPS |