| Upload Date | December 02 2025 08:11 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.6.2 |
| Model | iPhone 12 Mini |
| Model ID | iPhone13,1 |
| Motherboard | D52gAP |
| 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 | 3.61 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
386
71.9 IPS |
|
|
Image Classification (HP)
|
100% |
359
66.7 IPS |
|
|
Image Classification (Q)
|
96% |
324
60.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1758
28.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1837
29.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
1734
28.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
6134
7.16 IPS |
|
|
Pose Estimation (HP)
|
100% |
9246
10.8 IPS |
|
|
Pose Estimation (Q)
|
94% |
8331
9.77 IPS |
|
|
Object Detection (SP)
|
100% |
664
52.7 IPS |
|
|
Object Detection (HP)
|
100% |
673
53.4 IPS |
|
|
Object Detection (Q)
|
92% |
649
51.8 IPS |
|
|
Face Detection (SP)
|
100% |
3517
41.8 IPS |
|
|
Face Detection (HP)
|
100% |
3749
44.6 IPS |
|
|
Face Detection (Q)
|
100% |
3341
39.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
3809
29.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
5743
44.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
5360
41.9 IPS |
|
|
Style Transfer (SP)
|
100% |
12929
16.6 IPS |
|
|
Style Transfer (HP)
|
100% |
13711
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
13452
17.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1516
56.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1511
55.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1442
53.2 IPS |
|
|
Text Classification (SP)
|
100% |
2125
2.84 KIPS |
|
|
Text Classification (HP)
|
100% |
3660
4.88 KIPS |
|
|
Text Classification (Q)
|
93% |
3646
4.89 KIPS |
|
|
Machine Translation (SP)
|
100% |
503
8.66 IPS |
|
|
Machine Translation (HP)
|
100% |
515
8.88 IPS |
|
|
Machine Translation (Q)
|
98% |
509
8.80 IPS |