| Upload Date | December 04 2025 04:02 PM |
| Views | 7 |
| 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% |
404
75.2 IPS |
|
|
Image Classification (HP)
|
100% |
332
61.8 IPS |
|
|
Image Classification (Q)
|
96% |
306
57.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1385
22.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1718
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1716
27.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4159
4.85 IPS |
|
|
Pose Estimation (HP)
|
100% |
6952
8.11 IPS |
|
|
Pose Estimation (Q)
|
94% |
5581
6.54 IPS |
|
|
Object Detection (SP)
|
100% |
725
57.5 IPS |
|
|
Object Detection (HP)
|
100% |
613
48.6 IPS |
|
|
Object Detection (Q)
|
92% |
595
47.5 IPS |
|
|
Face Detection (SP)
|
100% |
2952
35.1 IPS |
|
|
Face Detection (HP)
|
100% |
3459
41.1 IPS |
|
|
Face Detection (Q)
|
100% |
2526
30.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
3528
27.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
4584
35.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
4053
31.7 IPS |
|
|
Style Transfer (SP)
|
100% |
11199
14.4 IPS |
|
|
Style Transfer (HP)
|
100% |
13735
17.7 IPS |
|
|
Style Transfer (Q)
|
96% |
13360
17.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1520
56.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1521
56.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1474
54.4 IPS |
|
|
Text Classification (SP)
|
100% |
1365
1.82 KIPS |
|
|
Text Classification (HP)
|
99% |
2361
3.15 KIPS |
|
|
Text Classification (Q)
|
93% |
2340
3.14 KIPS |
|
|
Machine Translation (SP)
|
100% |
489
8.42 IPS |
|
|
Machine Translation (HP)
|
100% |
503
8.66 IPS |
|
|
Machine Translation (Q)
|
98% |
500
8.65 IPS |