| Upload Date | November 12 2025 03:23 AM |
| Views | 1 |
| 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% |
364
67.7 IPS |
|
|
Image Classification (HP)
|
100% |
369
68.6 IPS |
|
|
Image Classification (Q)
|
96% |
343
64.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
1667
27.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1719
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1643
26.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
6146
7.17 IPS |
|
|
Pose Estimation (HP)
|
100% |
9540
11.1 IPS |
|
|
Pose Estimation (Q)
|
94% |
8679
10.2 IPS |
|
|
Object Detection (SP)
|
100% |
689
54.6 IPS |
|
|
Object Detection (HP)
|
100% |
628
49.8 IPS |
|
|
Object Detection (Q)
|
92% |
623
49.7 IPS |
|
|
Face Detection (SP)
|
100% |
3324
39.5 IPS |
|
|
Face Detection (HP)
|
100% |
3584
42.6 IPS |
|
|
Face Detection (Q)
|
100% |
3081
36.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
4220
32.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
5530
42.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
5196
40.6 IPS |
|
|
Style Transfer (SP)
|
100% |
12576
16.2 IPS |
|
|
Style Transfer (HP)
|
100% |
13651
17.5 IPS |
|
|
Style Transfer (Q)
|
96% |
13296
17.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1624
60.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1532
56.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1256
46.4 IPS |
|
|
Text Classification (SP)
|
100% |
2288
3.05 KIPS |
|
|
Text Classification (HP)
|
99% |
3778
5.04 KIPS |
|
|
Text Classification (Q)
|
93% |
3760
5.05 KIPS |
|
|
Machine Translation (SP)
|
100% |
496
8.54 IPS |
|
|
Machine Translation (HP)
|
100% |
514
8.85 IPS |
|
|
Machine Translation (Q)
|
98% |
503
8.69 IPS |