| Upload Date | November 12 2025 07:33 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,5 |
| Motherboard | J320AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.66 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
493
91.6 IPS |
|
|
Image Classification (HP)
|
100% |
811
150.8 IPS |
|
|
Image Classification (Q)
|
96% |
639
119.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
607
9.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
961
15.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
1012
16.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
2626
3.06 IPS |
|
|
Pose Estimation (HP)
|
100% |
2375
2.77 IPS |
|
|
Pose Estimation (Q)
|
96% |
1835
2.15 IPS |
|
|
Object Detection (SP)
|
100% |
541
42.9 IPS |
|
|
Object Detection (HP)
|
99% |
961
76.2 IPS |
|
|
Object Detection (Q)
|
92% |
755
60.2 IPS |
|
|
Face Detection (SP)
|
100% |
1261
15.0 IPS |
|
|
Face Detection (HP)
|
100% |
2332
27.7 IPS |
|
|
Face Detection (Q)
|
100% |
1528
18.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
1729
13.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
2682
20.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
2249
17.6 IPS |
|
|
Style Transfer (SP)
|
100% |
5093
6.55 IPS |
|
|
Style Transfer (HP)
|
100% |
7954
10.2 IPS |
|
|
Style Transfer (Q)
|
96% |
7139
9.21 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1249
46.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1515
56.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1249
46.1 IPS |
|
|
Text Classification (SP)
|
100% |
289
385.5 IPS |
|
|
Text Classification (HP)
|
100% |
552
736.4 IPS |
|
|
Text Classification (Q)
|
93% |
551
738.8 IPS |
|
|
Machine Translation (SP)
|
100% |
718
12.4 IPS |
|
|
Machine Translation (HP)
|
99% |
1264
21.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1262
21.8 IPS |