| Upload Date | February 13 2026 02:52 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| 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% |
377
70.1 IPS |
|
|
Image Classification (HP)
|
100% |
339
63.0 IPS |
|
|
Image Classification (Q)
|
94% |
321
60.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1393
22.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
1721
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1695
27.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
4212
4.91 IPS |
|
|
Pose Estimation (HP)
|
100% |
7019
8.19 IPS |
|
|
Pose Estimation (Q)
|
94% |
5795
6.79 IPS |
|
|
Object Detection (SP)
|
100% |
669
53.1 IPS |
|
|
Object Detection (HP)
|
100% |
632
50.1 IPS |
|
|
Object Detection (Q)
|
91% |
640
51.1 IPS |
|
|
Face Detection (SP)
|
100% |
2996
35.6 IPS |
|
|
Face Detection (HP)
|
100% |
3632
43.2 IPS |
|
|
Face Detection (Q)
|
100% |
2854
33.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
4262
32.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
5658
43.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
4174
32.6 IPS |
|
|
Style Transfer (SP)
|
100% |
11331
14.6 IPS |
|
|
Style Transfer (HP)
|
100% |
13718
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
13453
17.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1511
55.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1669
61.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1374
50.7 IPS |
|
|
Text Classification (SP)
|
100% |
1365
1.82 KIPS |
|
|
Text Classification (HP)
|
99% |
2342
3.13 KIPS |
|
|
Text Classification (Q)
|
93% |
2331
3.13 KIPS |
|
|
Machine Translation (SP)
|
100% |
601
10.3 IPS |
|
|
Machine Translation (HP)
|
100% |
634
10.9 IPS |
|
|
Machine Translation (Q)
|
98% |
568
9.82 IPS |