| Upload Date | November 22 2025 07:37 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
367
68.3 IPS |
|
|
Image Classification (HP)
|
100% |
361
67.2 IPS |
|
|
Image Classification (Q)
|
96% |
307
57.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1629
26.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
1719
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1652
26.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
5511
6.43 IPS |
|
|
Pose Estimation (HP)
|
100% |
6754
7.88 IPS |
|
|
Pose Estimation (Q)
|
94% |
5556
6.51 IPS |
|
|
Object Detection (SP)
|
100% |
633
50.2 IPS |
|
|
Object Detection (HP)
|
100% |
623
49.4 IPS |
|
|
Object Detection (Q)
|
92% |
618
49.3 IPS |
|
|
Face Detection (SP)
|
100% |
3255
38.7 IPS |
|
|
Face Detection (HP)
|
100% |
3232
38.4 IPS |
|
|
Face Detection (Q)
|
100% |
3103
36.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
3817
29.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
5518
42.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
4930
38.5 IPS |
|
|
Style Transfer (SP)
|
100% |
10853
14.0 IPS |
|
|
Style Transfer (HP)
|
100% |
11453
14.7 IPS |
|
|
Style Transfer (Q)
|
96% |
11713
15.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1468
54.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1443
53.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1400
51.7 IPS |
|
|
Text Classification (SP)
|
100% |
2169
2.89 KIPS |
|
|
Text Classification (HP)
|
99% |
3618
4.83 KIPS |
|
|
Text Classification (Q)
|
93% |
3588
4.82 KIPS |
|
|
Machine Translation (SP)
|
100% |
497
8.56 IPS |
|
|
Machine Translation (HP)
|
100% |
507
8.74 IPS |
|
|
Machine Translation (Q)
|
98% |
508
8.77 IPS |