| User | Boldi2010 |
| Upload Date | December 30 2025 08:26 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| 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% |
877
163.0 IPS |
|
|
Image Classification (HP)
|
100% |
1162
216.0 IPS |
|
|
Image Classification (Q)
|
96% |
153
28.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
355
5.75 IPS |
|
|
Image Segmentation (HP)
|
100% |
384
6.22 IPS |
|
|
Image Segmentation (Q)
|
99% |
219
3.55 IPS |
|
|
Pose Estimation (SP)
|
100% |
2802
3.27 IPS |
|
|
Pose Estimation (HP)
|
100% |
3974
4.64 IPS |
|
|
Pose Estimation (Q)
|
96% |
1693
1.98 IPS |
|
|
Object Detection (SP)
|
100% |
912
72.3 IPS |
|
|
Object Detection (HP)
|
100% |
1210
96.0 IPS |
|
|
Object Detection (Q)
|
92% |
177
14.1 IPS |
|
|
Face Detection (SP)
|
100% |
3353
39.8 IPS |
|
|
Face Detection (HP)
|
100% |
3811
45.3 IPS |
|
|
Face Detection (Q)
|
100% |
293
3.49 IPS |
|
|
Depth Estimation (SP)
|
100% |
2838
21.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
4022
31.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
535
4.18 IPS |
|
|
Style Transfer (SP)
|
100% |
7864
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9570
12.3 IPS |
|
|
Style Transfer (Q)
|
96% |
3025
3.90 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1366
50.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1825
67.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
392
14.5 IPS |
|
|
Text Classification (SP)
|
100% |
98
131.4 IPS |
|
|
Text Classification (HP)
|
100% |
98
131.2 IPS |
|
|
Text Classification (Q)
|
93% |
101
135.2 IPS |
|
|
Machine Translation (SP)
|
100% |
532
9.16 IPS |
|
|
Machine Translation (HP)
|
100% |
484
8.34 IPS |
|
|
Machine Translation (Q)
|
98% |
475
8.21 IPS |