| Upload Date | October 18 2025 01:37 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 8 Elite |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Samsung Galaxy S25 |
| Model ID | samsung SM-S931B |
| 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% |
1811
336.8 IPS |
|
|
Image Classification (HP)
|
100% |
2754
512.2 IPS |
|
|
Image Classification (Q)
|
100% |
2650
492.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
3623
58.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
6799
110.2 IPS |
|
|
Image Segmentation (Q)
|
98% |
6554
106.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
13871
16.2 IPS |
|
|
Pose Estimation (HP)
|
99% |
24813
29.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
9807
11.5 IPS |
|
|
Object Detection (SP)
|
100% |
1012
80.3 IPS |
|
|
Object Detection (HP)
|
99% |
1257
99.7 IPS |
|
|
Object Detection (Q)
|
85% |
1280
103.0 IPS |
|
|
Face Detection (SP)
|
100% |
3682
43.7 IPS |
|
|
Face Detection (HP)
|
100% |
5801
68.9 IPS |
|
|
Face Detection (Q)
|
97% |
5135
61.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4160
32.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
5992
46.3 IPS |
|
|
Depth Estimation (Q)
|
61% |
5238
51.0 IPS |
|
|
Style Transfer (SP)
|
100% |
12011
15.4 IPS |
|
|
Style Transfer (HP)
|
100% |
24654
31.7 IPS |
|
|
Style Transfer (Q)
|
98% |
22372
28.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2322
85.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3705
136.8 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
3600
133.4 IPS |
|
|
Text Classification (SP)
|
35% |
55
536.1 IPS |
|
|
Text Classification (HP)
|
35% |
96
871.8 IPS |
|
|
Text Classification (Q)
|
33% |
61
685.7 IPS |
|
|
Machine Translation (SP)
|
100% |
1067
18.4 IPS |
|
|
Machine Translation (HP)
|
100% |
984
16.9 IPS |
|
|
Machine Translation (Q)
|
48% |
427
16.4 IPS |