| Upload Date | November 12 2025 05:51 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
387
72.0 IPS |
|
|
Image Classification (HP)
|
100% |
652
121.3 IPS |
|
|
Image Classification (Q)
|
96% |
535
99.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
402
6.52 IPS |
|
|
Image Segmentation (HP)
|
100% |
686
11.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
765
12.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
1135
1.32 IPS |
|
|
Pose Estimation (HP)
|
100% |
1069
1.25 IPS |
|
|
Pose Estimation (Q)
|
96% |
1030
1.21 IPS |
|
|
Object Detection (SP)
|
100% |
341
27.0 IPS |
|
|
Object Detection (HP)
|
99% |
683
54.2 IPS |
|
|
Object Detection (Q)
|
92% |
570
45.5 IPS |
|
|
Face Detection (SP)
|
100% |
921
10.9 IPS |
|
|
Face Detection (HP)
|
100% |
1757
20.9 IPS |
|
|
Face Detection (Q)
|
100% |
1167
13.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
932
7.18 IPS |
|
|
Depth Estimation (HP)
|
98% |
1618
12.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
1395
10.9 IPS |
|
|
Style Transfer (SP)
|
100% |
2207
2.84 IPS |
|
|
Style Transfer (HP)
|
100% |
3769
4.84 IPS |
|
|
Style Transfer (Q)
|
96% |
3776
4.87 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
636
23.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
848
31.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
754
27.8 IPS |
|
|
Text Classification (SP)
|
100% |
282
375.8 IPS |
|
|
Text Classification (HP)
|
100% |
566
755.2 IPS |
|
|
Text Classification (Q)
|
93% |
563
755.8 IPS |
|
|
Machine Translation (SP)
|
100% |
611
10.5 IPS |
|
|
Machine Translation (HP)
|
99% |
984
16.9 IPS |
|
|
Machine Translation (Q)
|
98% |
1054
18.2 IPS |