| Upload Date | December 14 2025 04:46 AM |
| Views | 3 |
| 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% |
663
123.3 IPS |
|
|
Image Classification (HP)
|
100% |
1099
204.3 IPS |
|
|
Image Classification (Q)
|
96% |
789
147.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
753
12.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1122
18.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
1298
21.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
3118
3.64 IPS |
|
|
Pose Estimation (HP)
|
100% |
6745
7.87 IPS |
|
|
Pose Estimation (Q)
|
95% |
6408
7.51 IPS |
|
|
Object Detection (SP)
|
100% |
699
55.4 IPS |
|
|
Object Detection (HP)
|
97% |
1224
97.5 IPS |
|
|
Object Detection (Q)
|
94% |
890
70.9 IPS |
|
|
Face Detection (SP)
|
100% |
1675
19.9 IPS |
|
|
Face Detection (HP)
|
100% |
2914
34.6 IPS |
|
|
Face Detection (Q)
|
100% |
1705
20.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
2625
20.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
5062
39.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
3683
28.8 IPS |
|
|
Style Transfer (SP)
|
100% |
7993
10.3 IPS |
|
|
Style Transfer (HP)
|
100% |
13684
17.6 IPS |
|
|
Style Transfer (Q)
|
96% |
11465
14.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1957
72.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2387
88.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1899
70.1 IPS |
|
|
Text Classification (SP)
|
100% |
1372
1.83 KIPS |
|
|
Text Classification (HP)
|
99% |
2381
3.18 KIPS |
|
|
Text Classification (Q)
|
93% |
2375
3.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
1441
24.8 IPS |
|
|
Machine Translation (HP)
|
98% |
2881
49.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2858
49.4 IPS |