| Upload Date | November 21 2026 05:08 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| 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% |
352
65.5 IPS |
|
|
Image Classification (HP)
|
100% |
372
69.1 IPS |
|
|
Image Classification (Q)
|
94% |
344
64.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1678
27.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1685
27.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
1441
23.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
4973
5.80 IPS |
|
|
Pose Estimation (HP)
|
100% |
8239
9.61 IPS |
|
|
Pose Estimation (Q)
|
94% |
6956
8.16 IPS |
|
|
Object Detection (SP)
|
100% |
642
50.9 IPS |
|
|
Object Detection (HP)
|
100% |
644
51.1 IPS |
|
|
Object Detection (Q)
|
91% |
602
48.1 IPS |
|
|
Face Detection (SP)
|
100% |
3425
40.7 IPS |
|
|
Face Detection (HP)
|
100% |
3739
44.4 IPS |
|
|
Face Detection (Q)
|
100% |
3455
41.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
3792
29.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
5547
42.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
5046
39.5 IPS |
|
|
Style Transfer (SP)
|
100% |
12677
16.3 IPS |
|
|
Style Transfer (HP)
|
100% |
13525
17.4 IPS |
|
|
Style Transfer (Q)
|
96% |
11782
15.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1581
58.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1315
48.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1296
47.8 IPS |
|
|
Text Classification (SP)
|
99% |
4090
5.46 KIPS |
|
|
Text Classification (HP)
|
100% |
6460
8.62 KIPS |
|
|
Text Classification (Q)
|
93% |
6596
8.85 KIPS |
|
|
Machine Translation (SP)
|
100% |
620
10.7 IPS |
|
|
Machine Translation (HP)
|
100% |
647
11.1 IPS |
|
|
Machine Translation (Q)
|
98% |
572
9.89 IPS |