| Upload Date | February 01 2026 01:00 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
390
72.5 IPS |
|
|
Image Classification (HP)
|
100% |
552
102.6 IPS |
|
|
Image Classification (Q)
|
96% |
549
102.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
414
6.71 IPS |
|
|
Image Segmentation (HP)
|
100% |
734
11.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
806
13.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
1214
1.42 IPS |
|
|
Pose Estimation (HP)
|
100% |
1224
1.43 IPS |
|
|
Pose Estimation (Q)
|
96% |
1178
1.38 IPS |
|
|
Object Detection (SP)
|
100% |
372
29.5 IPS |
|
|
Object Detection (HP)
|
99% |
727
57.7 IPS |
|
|
Object Detection (Q)
|
92% |
617
49.2 IPS |
|
|
Face Detection (SP)
|
100% |
940
11.2 IPS |
|
|
Face Detection (HP)
|
100% |
1855
22.0 IPS |
|
|
Face Detection (Q)
|
100% |
1231
14.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
998
7.69 IPS |
|
|
Depth Estimation (HP)
|
98% |
1723
13.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
1559
12.2 IPS |
|
|
Style Transfer (SP)
|
100% |
2538
3.26 IPS |
|
|
Style Transfer (HP)
|
100% |
4229
5.44 IPS |
|
|
Style Transfer (Q)
|
96% |
4030
5.20 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
682
25.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
936
34.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
801
29.6 IPS |
|
|
Text Classification (SP)
|
100% |
293
391.1 IPS |
|
|
Text Classification (HP)
|
100% |
568
758.2 IPS |
|
|
Text Classification (Q)
|
93% |
565
758.4 IPS |
|
|
Machine Translation (SP)
|
100% |
620
10.7 IPS |
|
|
Machine Translation (HP)
|
99% |
1091
18.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1102
19.1 IPS |