| Upload Date | December 09 2025 10:01 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| 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% |
539
100.3 IPS |
|
|
Image Classification (HP)
|
100% |
855
158.9 IPS |
|
|
Image Classification (Q)
|
96% |
626
117.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
655
10.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
868
14.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
1015
16.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
2672
3.12 IPS |
|
|
Pose Estimation (HP)
|
100% |
5953
6.95 IPS |
|
|
Pose Estimation (Q)
|
95% |
5090
5.97 IPS |
|
|
Object Detection (SP)
|
100% |
583
46.3 IPS |
|
|
Object Detection (HP)
|
97% |
939
74.8 IPS |
|
|
Object Detection (Q)
|
94% |
698
55.7 IPS |
|
|
Face Detection (SP)
|
100% |
1361
16.2 IPS |
|
|
Face Detection (HP)
|
100% |
2234
26.5 IPS |
|
|
Face Detection (Q)
|
100% |
1311
15.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
2241
17.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
4020
31.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
2860
22.4 IPS |
|
|
Style Transfer (SP)
|
100% |
7109
9.14 IPS |
|
|
Style Transfer (HP)
|
100% |
11142
14.3 IPS |
|
|
Style Transfer (Q)
|
96% |
9278
12.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1580
58.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2081
76.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1466
54.1 IPS |
|
|
Text Classification (SP)
|
100% |
1042
1.39 KIPS |
|
|
Text Classification (HP)
|
100% |
1797
2.40 KIPS |
|
|
Text Classification (Q)
|
93% |
1791
2.40 KIPS |
|
|
Machine Translation (SP)
|
100% |
1209
20.8 IPS |
|
|
Machine Translation (HP)
|
98% |
2171
37.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2169
37.5 IPS |