| Upload Date | November 09 2025 03:04 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| 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 | 2.88 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
223
41.4 IPS |
|
|
Image Classification (HP)
|
100% |
2131
396.3 IPS |
|
|
Image Classification (Q)
|
99% |
151
28.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
216
3.49 IPS |
|
|
Image Segmentation (HP)
|
100% |
362
5.87 IPS |
|
|
Image Segmentation (Q)
|
99% |
165
2.67 IPS |
|
|
Pose Estimation (SP)
|
100% |
852
0.99 IPS |
|
|
Pose Estimation (HP)
|
100% |
21901
25.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
714
0.84 IPS |
|
|
Object Detection (SP)
|
100% |
237
18.8 IPS |
|
|
Object Detection (HP)
|
100% |
1364
108.2 IPS |
|
|
Object Detection (Q)
|
94% |
176
14.1 IPS |
|
|
Face Detection (SP)
|
100% |
577
6.86 IPS |
|
|
Face Detection (HP)
|
100% |
5201
61.8 IPS |
|
|
Face Detection (Q)
|
100% |
213
2.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
594
4.58 IPS |
|
|
Depth Estimation (HP)
|
99% |
18604
143.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
419
3.27 IPS |
|
|
Style Transfer (SP)
|
100% |
1660
2.13 IPS |
|
|
Style Transfer (HP)
|
100% |
1664
2.14 IPS |
|
|
Style Transfer (Q)
|
96% |
1372
1.77 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
562
20.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3184
117.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
439
16.2 IPS |
|
|
Text Classification (SP)
|
100% |
260
346.6 IPS |
|
|
Text Classification (HP)
|
100% |
285
379.9 IPS |
|
|
Text Classification (Q)
|
93% |
279
374.9 IPS |
|
|
Machine Translation (SP)
|
100% |
409
7.05 IPS |
|
|
Machine Translation (HP)
|
100% |
295
5.09 IPS |
|
|
Machine Translation (Q)
|
98% |
291
5.04 IPS |