| Upload Date | October 26 2025 12:32 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.0.1 |
| Model | iPad mini (5th generation) |
| Model ID | iPad11,1 |
| Motherboard | J210AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.85 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
384
71.5 IPS |
|
|
Image Classification (HP)
|
100% |
652
121.2 IPS |
|
|
Image Classification (Q)
|
96% |
535
99.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
418
6.78 IPS |
|
|
Image Segmentation (HP)
|
100% |
707
11.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
773
12.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
1154
1.35 IPS |
|
|
Pose Estimation (HP)
|
100% |
1141
1.33 IPS |
|
|
Pose Estimation (Q)
|
96% |
1075
1.26 IPS |
|
|
Object Detection (SP)
|
100% |
354
28.1 IPS |
|
|
Object Detection (HP)
|
99% |
683
54.1 IPS |
|
|
Object Detection (Q)
|
92% |
597
47.7 IPS |
|
|
Face Detection (SP)
|
100% |
918
10.9 IPS |
|
|
Face Detection (HP)
|
100% |
1792
21.3 IPS |
|
|
Face Detection (Q)
|
100% |
1203
14.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
936
7.21 IPS |
|
|
Depth Estimation (HP)
|
98% |
1623
12.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
1416
11.1 IPS |
|
|
Style Transfer (SP)
|
100% |
2345
3.01 IPS |
|
|
Style Transfer (HP)
|
100% |
3917
5.04 IPS |
|
|
Style Transfer (Q)
|
96% |
3717
4.80 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
637
23.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
870
32.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
758
28.0 IPS |
|
|
Text Classification (SP)
|
100% |
290
387.7 IPS |
|
|
Text Classification (HP)
|
100% |
568
758.1 IPS |
|
|
Text Classification (Q)
|
93% |
565
758.4 IPS |
|
|
Machine Translation (SP)
|
100% |
618
10.6 IPS |
|
|
Machine Translation (HP)
|
99% |
1003
17.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1012
17.5 IPS |