| User | fredstar |
| Upload Date | February 08 2026 12:43 PM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 8 Gen 1 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Samsung Galaxy Tab S8 |
| Model ID | samsung SM-X700 |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.50 GHz |
| Cluster 3 | 1 Core @ 3.00 GHz |
| Memory Information | |
|---|---|
| Size | 7.12 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
900
167.4 IPS |
|
|
Image Classification (HP)
|
100% |
1392
259.0 IPS |
|
|
Image Classification (Q)
|
99% |
1228
229.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1648
26.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2683
43.5 IPS |
|
|
Image Segmentation (Q)
|
98% |
2199
35.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
6147
7.17 IPS |
|
|
Pose Estimation (HP)
|
99% |
11524
13.4 IPS |
|
|
Pose Estimation (Q)
|
97% |
11133
13.0 IPS |
|
|
Object Detection (SP)
|
100% |
671
53.2 IPS |
|
|
Object Detection (HP)
|
99% |
1154
91.5 IPS |
|
|
Object Detection (Q)
|
85% |
1087
87.5 IPS |
|
|
Face Detection (SP)
|
100% |
2399
28.5 IPS |
|
|
Face Detection (HP)
|
100% |
4925
58.5 IPS |
|
|
Face Detection (Q)
|
97% |
3902
46.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
3041
23.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
5327
41.2 IPS |
|
|
Depth Estimation (Q)
|
65% |
4386
39.4 IPS |
|
|
Style Transfer (SP)
|
100% |
7174
9.22 IPS |
|
|
Style Transfer (HP)
|
100% |
14103
18.1 IPS |
|
|
Style Transfer (Q)
|
98% |
13831
17.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1295
47.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2833
104.6 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2682
99.4 IPS |
|
|
Text Classification (SP)
|
35% |
46
448.2 IPS |
|
|
Text Classification (HP)
|
35% |
65
589.6 IPS |
|
|
Text Classification (Q)
|
35% |
64
585.9 IPS |
|
|
Machine Translation (SP)
|
100% |
532
9.16 IPS |
|
|
Machine Translation (HP)
|
97% |
631
10.9 IPS |
|
|
Machine Translation (Q)
|
64% |
429
8.82 IPS |