| Upload Date | November 10 2025 06:47 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,1 |
| Motherboard | J317AP |
| 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 | 3.70 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
908
168.9 IPS |
|
|
Image Classification (HP)
|
100% |
1206
224.3 IPS |
|
|
Image Classification (Q)
|
96% |
153
28.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
360
5.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
375
6.08 IPS |
|
|
Image Segmentation (Q)
|
99% |
219
3.55 IPS |
|
|
Pose Estimation (SP)
|
100% |
2804
3.27 IPS |
|
|
Pose Estimation (HP)
|
100% |
3973
4.64 IPS |
|
|
Pose Estimation (Q)
|
96% |
1698
1.99 IPS |
|
|
Object Detection (SP)
|
100% |
908
72.0 IPS |
|
|
Object Detection (HP)
|
100% |
1212
96.1 IPS |
|
|
Object Detection (Q)
|
92% |
177
14.2 IPS |
|
|
Face Detection (SP)
|
100% |
3351
39.8 IPS |
|
|
Face Detection (HP)
|
100% |
4003
47.6 IPS |
|
|
Face Detection (Q)
|
100% |
297
3.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
2867
22.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
4097
31.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
530
4.14 IPS |
|
|
Style Transfer (SP)
|
100% |
7881
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9775
12.6 IPS |
|
|
Style Transfer (Q)
|
96% |
2960
3.82 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1355
50.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1795
66.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
394
14.5 IPS |
|
|
Text Classification (SP)
|
100% |
92
122.7 IPS |
|
|
Text Classification (HP)
|
100% |
103
138.0 IPS |
|
|
Text Classification (Q)
|
93% |
99
133.5 IPS |
|
|
Machine Translation (SP)
|
100% |
529
9.11 IPS |
|
|
Machine Translation (HP)
|
100% |
473
8.15 IPS |
|
|
Machine Translation (Q)
|
98% |
472
8.15 IPS |