| Upload Date | February 01 2026 12:52 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2.1 |
| 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% |
397
73.8 IPS |
|
|
Image Classification (HP)
|
100% |
376
69.8 IPS |
|
|
Image Classification (Q)
|
96% |
338
63.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
1691
27.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
1771
28.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1728
28.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
6240
7.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
8997
10.5 IPS |
|
|
Pose Estimation (Q)
|
94% |
7902
9.27 IPS |
|
|
Object Detection (SP)
|
100% |
655
52.0 IPS |
|
|
Object Detection (HP)
|
100% |
623
49.4 IPS |
|
|
Object Detection (Q)
|
92% |
652
52.0 IPS |
|
|
Face Detection (SP)
|
100% |
3285
39.0 IPS |
|
|
Face Detection (HP)
|
100% |
3466
41.2 IPS |
|
|
Face Detection (Q)
|
100% |
3111
37.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
3997
30.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
5548
42.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
5219
40.8 IPS |
|
|
Style Transfer (SP)
|
100% |
13033
16.8 IPS |
|
|
Style Transfer (HP)
|
100% |
13717
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
13327
17.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1589
58.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1427
52.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1480
54.6 IPS |
|
|
Text Classification (SP)
|
100% |
2295
3.06 KIPS |
|
|
Text Classification (HP)
|
99% |
3911
5.22 KIPS |
|
|
Text Classification (Q)
|
93% |
3897
5.23 KIPS |
|
|
Machine Translation (SP)
|
100% |
493
8.48 IPS |
|
|
Machine Translation (HP)
|
100% |
505
8.70 IPS |
|
|
Machine Translation (Q)
|
98% |
511
8.82 IPS |