| Upload Date | October 06 2025 05:02 PM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.6.1 |
| Model | iPhone 12 |
| Model ID | iPhone13,2 |
| Motherboard | D53gAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
360
67.0 IPS |
|
|
Image Classification (HP)
|
100% |
349
64.8 IPS |
|
|
Image Classification (Q)
|
96% |
335
62.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1672
27.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1672
27.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
1579
25.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
6147
7.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
9412
11.0 IPS |
|
|
Pose Estimation (Q)
|
94% |
8477
9.94 IPS |
|
|
Object Detection (SP)
|
100% |
692
54.9 IPS |
|
|
Object Detection (HP)
|
100% |
630
50.0 IPS |
|
|
Object Detection (Q)
|
92% |
642
51.3 IPS |
|
|
Face Detection (SP)
|
100% |
3222
38.3 IPS |
|
|
Face Detection (HP)
|
100% |
3415
40.6 IPS |
|
|
Face Detection (Q)
|
100% |
3157
37.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
3778
29.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
5644
43.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
5236
40.9 IPS |
|
|
Style Transfer (SP)
|
100% |
12634
16.2 IPS |
|
|
Style Transfer (HP)
|
100% |
13602
17.5 IPS |
|
|
Style Transfer (Q)
|
96% |
13184
17.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1512
55.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1545
57.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1425
52.6 IPS |
|
|
Text Classification (SP)
|
100% |
2095
2.80 KIPS |
|
|
Text Classification (HP)
|
100% |
3662
4.89 KIPS |
|
|
Text Classification (Q)
|
93% |
3646
4.89 KIPS |
|
|
Machine Translation (SP)
|
100% |
486
8.37 IPS |
|
|
Machine Translation (HP)
|
100% |
496
8.54 IPS |
|
|
Machine Translation (Q)
|
98% |
484
8.36 IPS |