| Upload Date | January 05 2026 10:05 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad (9th generation) |
| Model ID | iPad12,1 |
| Motherboard | J181AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.87 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
295
55.0 IPS |
|
|
Image Classification (HP)
|
100% |
383
71.3 IPS |
|
|
Image Classification (Q)
|
97% |
242
45.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
311
5.04 IPS |
|
|
Image Segmentation (HP)
|
100% |
343
5.56 IPS |
|
|
Image Segmentation (Q)
|
99% |
345
5.59 IPS |
|
|
Pose Estimation (SP)
|
100% |
2372
2.77 IPS |
|
|
Pose Estimation (HP)
|
100% |
3213
3.75 IPS |
|
|
Pose Estimation (Q)
|
95% |
1257
1.47 IPS |
|
|
Object Detection (SP)
|
100% |
644
51.1 IPS |
|
|
Object Detection (HP)
|
100% |
652
51.7 IPS |
|
|
Object Detection (Q)
|
94% |
300
23.9 IPS |
|
|
Face Detection (SP)
|
100% |
2531
30.1 IPS |
|
|
Face Detection (HP)
|
100% |
3355
39.9 IPS |
|
|
Face Detection (Q)
|
100% |
392
4.65 IPS |
|
|
Depth Estimation (SP)
|
100% |
2533
19.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
3396
26.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
1033
8.07 IPS |
|
|
Style Transfer (SP)
|
100% |
6174
7.94 IPS |
|
|
Style Transfer (HP)
|
100% |
8703
11.2 IPS |
|
|
Style Transfer (Q)
|
96% |
2102
2.71 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1198
44.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1341
49.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
461
17.0 IPS |
|
|
Text Classification (SP)
|
100% |
98
131.1 IPS |
|
|
Text Classification (HP)
|
100% |
391
522.5 IPS |
|
|
Text Classification (Q)
|
93% |
392
525.7 IPS |
|
|
Machine Translation (SP)
|
100% |
336
5.79 IPS |
|
|
Machine Translation (HP)
|
100% |
259
4.45 IPS |
|
|
Machine Translation (Q)
|
98% |
249
4.30 IPS |