| User | Beamish |
| Upload Date | February 06 2026 09:11 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 888 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | Samsung Galaxy Z Flip3 |
| Model ID | samsung SM-F711B |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 7.22 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
405
75.4 IPS |
|
|
Image Classification (HP)
|
100% |
605
112.5 IPS |
|
|
Image Classification (Q)
|
99% |
548
102.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
730
11.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
1152
18.7 IPS |
|
|
Image Segmentation (Q)
|
98% |
900
14.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2705
3.16 IPS |
|
|
Pose Estimation (HP)
|
99% |
4665
5.44 IPS |
|
|
Pose Estimation (Q)
|
97% |
4586
5.37 IPS |
|
|
Object Detection (SP)
|
100% |
307
24.4 IPS |
|
|
Object Detection (HP)
|
99% |
407
32.3 IPS |
|
|
Object Detection (Q)
|
85% |
382
30.8 IPS |
|
|
Face Detection (SP)
|
100% |
1057
12.6 IPS |
|
|
Face Detection (HP)
|
100% |
1559
18.5 IPS |
|
|
Face Detection (Q)
|
97% |
2464
29.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
2345
18.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
3362
26.0 IPS |
|
|
Depth Estimation (Q)
|
63% |
2686
24.8 IPS |
|
|
Style Transfer (SP)
|
100% |
5863
7.54 IPS |
|
|
Style Transfer (HP)
|
100% |
11074
14.2 IPS |
|
|
Style Transfer (Q)
|
98% |
10903
14.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1102
40.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1549
57.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1593
59.0 IPS |
|
|
Text Classification (SP)
|
35% |
32
313.4 IPS |
|
|
Text Classification (HP)
|
35% |
44
398.5 IPS |
|
|
Text Classification (Q)
|
35% |
43
387.5 IPS |
|
|
Machine Translation (SP)
|
100% |
250
4.31 IPS |
|
|
Machine Translation (HP)
|
97% |
339
5.87 IPS |
|
|
Machine Translation (Q)
|
64% |
266
5.47 IPS |