| Upload Date | December 17 2025 06:47 PM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
1229
228.6 IPS |
|
|
Image Classification (HP)
|
100% |
2031
377.6 IPS |
|
|
Image Classification (Q)
|
96% |
1451
271.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1101
17.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
1722
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2131
34.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
4751
5.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
10219
11.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
9155
10.7 IPS |
|
|
Object Detection (SP)
|
100% |
1165
92.4 IPS |
|
|
Object Detection (HP)
|
97% |
2199
175.0 IPS |
|
|
Object Detection (Q)
|
94% |
1592
126.9 IPS |
|
|
Face Detection (SP)
|
100% |
2517
29.9 IPS |
|
|
Face Detection (HP)
|
100% |
4588
54.5 IPS |
|
|
Face Detection (Q)
|
100% |
2637
31.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
4554
35.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
9086
70.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
6315
49.4 IPS |
|
|
Style Transfer (SP)
|
100% |
12687
16.3 IPS |
|
|
Style Transfer (HP)
|
100% |
21500
27.6 IPS |
|
|
Style Transfer (Q)
|
96% |
18776
24.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2643
97.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4125
152.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3148
116.2 IPS |
|
|
Text Classification (SP)
|
100% |
2314
3.09 KIPS |
|
|
Text Classification (HP)
|
99% |
3971
5.30 KIPS |
|
|
Text Classification (Q)
|
93% |
3889
5.22 KIPS |
|
|
Machine Translation (SP)
|
100% |
2234
38.5 IPS |
|
|
Machine Translation (HP)
|
98% |
4232
73.1 IPS |
|
|
Machine Translation (Q)
|
98% |
4212
72.8 IPS |