| Upload Date | November 24 2025 04:21 PM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
374
69.6 IPS |
|
|
Image Classification (HP)
|
100% |
333
61.9 IPS |
|
|
Image Classification (Q)
|
96% |
326
60.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1395
22.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
1709
27.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1695
27.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
4152
4.84 IPS |
|
|
Pose Estimation (HP)
|
100% |
6853
8.00 IPS |
|
|
Pose Estimation (Q)
|
94% |
5803
6.80 IPS |
|
|
Object Detection (SP)
|
100% |
639
50.7 IPS |
|
|
Object Detection (HP)
|
100% |
638
50.6 IPS |
|
|
Object Detection (Q)
|
92% |
618
49.3 IPS |
|
|
Face Detection (SP)
|
100% |
2891
34.4 IPS |
|
|
Face Detection (HP)
|
100% |
3376
40.1 IPS |
|
|
Face Detection (Q)
|
100% |
2535
30.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
3465
26.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
4620
35.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
4125
32.2 IPS |
|
|
Style Transfer (SP)
|
100% |
11272
14.5 IPS |
|
|
Style Transfer (HP)
|
100% |
13698
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
13336
17.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1571
58.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1483
54.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1412
52.1 IPS |
|
|
Text Classification (SP)
|
100% |
1359
1.81 KIPS |
|
|
Text Classification (HP)
|
99% |
2349
3.13 KIPS |
|
|
Text Classification (Q)
|
93% |
2329
3.13 KIPS |
|
|
Machine Translation (SP)
|
100% |
488
8.41 IPS |
|
|
Machine Translation (HP)
|
100% |
495
8.52 IPS |
|
|
Machine Translation (Q)
|
98% |
500
8.65 IPS |