| Upload Date | November 11 2025 03:43 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPhone SE (2nd generation) |
| Model ID | iPhone12,8 |
| Motherboard | D79AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.89 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
300
55.7 IPS |
|
|
Image Classification (HP)
|
100% |
395
73.5 IPS |
|
|
Image Classification (Q)
|
97% |
242
45.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
313
5.07 IPS |
|
|
Image Segmentation (HP)
|
100% |
335
5.43 IPS |
|
|
Image Segmentation (Q)
|
99% |
298
4.83 IPS |
|
|
Pose Estimation (SP)
|
100% |
1787
2.08 IPS |
|
|
Pose Estimation (HP)
|
100% |
2322
2.71 IPS |
|
|
Pose Estimation (Q)
|
95% |
1239
1.45 IPS |
|
|
Object Detection (SP)
|
100% |
632
50.1 IPS |
|
|
Object Detection (HP)
|
100% |
644
51.1 IPS |
|
|
Object Detection (Q)
|
94% |
273
21.8 IPS |
|
|
Face Detection (SP)
|
100% |
2544
30.2 IPS |
|
|
Face Detection (HP)
|
100% |
3331
39.6 IPS |
|
|
Face Detection (Q)
|
100% |
350
4.15 IPS |
|
|
Depth Estimation (SP)
|
100% |
2429
18.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
2984
23.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
815
6.36 IPS |
|
|
Style Transfer (SP)
|
100% |
5791
7.44 IPS |
|
|
Style Transfer (HP)
|
100% |
5613
7.22 IPS |
|
|
Style Transfer (Q)
|
96% |
2086
2.69 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1169
43.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1246
46.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
437
16.2 IPS |
|
|
Text Classification (SP)
|
100% |
98
130.5 IPS |
|
|
Text Classification (HP)
|
100% |
400
533.5 IPS |
|
|
Text Classification (Q)
|
93% |
393
527.2 IPS |
|
|
Machine Translation (SP)
|
100% |
332
5.73 IPS |
|
|
Machine Translation (HP)
|
100% |
263
4.53 IPS |
|
|
Machine Translation (Q)
|
98% |
249
4.31 IPS |