| User | jobieh |
| Upload Date | November 12 2025 08:37 PM |
| Views | 4 |
| 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% |
273
50.7 IPS |
|
|
Image Classification (HP)
|
100% |
467
86.8 IPS |
|
|
Image Classification (Q)
|
96% |
402
75.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
274
4.44 IPS |
|
|
Image Segmentation (HP)
|
100% |
489
7.92 IPS |
|
|
Image Segmentation (Q)
|
99% |
629
10.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
684
0.80 IPS |
|
|
Pose Estimation (HP)
|
100% |
741
0.86 IPS |
|
|
Pose Estimation (Q)
|
96% |
808
0.95 IPS |
|
|
Object Detection (SP)
|
100% |
306
24.3 IPS |
|
|
Object Detection (HP)
|
99% |
636
50.4 IPS |
|
|
Object Detection (Q)
|
92% |
480
38.3 IPS |
|
|
Face Detection (SP)
|
100% |
780
9.27 IPS |
|
|
Face Detection (HP)
|
100% |
1504
17.9 IPS |
|
|
Face Detection (Q)
|
100% |
1046
12.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
704
5.42 IPS |
|
|
Depth Estimation (HP)
|
98% |
1308
10.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
1182
9.23 IPS |
|
|
Style Transfer (SP)
|
100% |
1843
2.37 IPS |
|
|
Style Transfer (HP)
|
100% |
2206
2.84 IPS |
|
|
Style Transfer (Q)
|
96% |
3350
4.32 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
538
19.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
716
26.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
681
25.1 IPS |
|
|
Text Classification (SP)
|
100% |
284
379.1 IPS |
|
|
Text Classification (HP)
|
100% |
572
763.7 IPS |
|
|
Text Classification (Q)
|
93% |
555
745.1 IPS |
|
|
Machine Translation (SP)
|
100% |
555
9.56 IPS |
|
|
Machine Translation (HP)
|
99% |
966
16.6 IPS |
|
|
Machine Translation (Q)
|
98% |
959
16.6 IPS |