| Upload Date | October 18 2025 03:56 PM |
| Views | 4 |
| 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% |
498
92.6 IPS |
|
|
Image Classification (HP)
|
100% |
795
147.9 IPS |
|
|
Image Classification (Q)
|
96% |
634
118.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
605
9.81 IPS |
|
|
Image Segmentation (HP)
|
100% |
953
15.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
1009
16.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
2575
3.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
2352
2.74 IPS |
|
|
Pose Estimation (Q)
|
96% |
2036
2.39 IPS |
|
|
Object Detection (SP)
|
100% |
541
42.9 IPS |
|
|
Object Detection (HP)
|
99% |
936
74.2 IPS |
|
|
Object Detection (Q)
|
92% |
760
60.6 IPS |
|
|
Face Detection (SP)
|
100% |
1251
14.9 IPS |
|
|
Face Detection (HP)
|
100% |
2312
27.5 IPS |
|
|
Face Detection (Q)
|
100% |
1470
17.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
1746
13.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
2660
20.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
2226
17.4 IPS |
|
|
Style Transfer (SP)
|
100% |
5119
6.58 IPS |
|
|
Style Transfer (HP)
|
100% |
7908
10.2 IPS |
|
|
Style Transfer (Q)
|
96% |
7128
9.20 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1221
45.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1229
45.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1215
44.9 IPS |
|
|
Text Classification (SP)
|
100% |
290
387.6 IPS |
|
|
Text Classification (HP)
|
100% |
553
738.7 IPS |
|
|
Text Classification (Q)
|
93% |
552
740.4 IPS |
|
|
Machine Translation (SP)
|
100% |
715
12.3 IPS |
|
|
Machine Translation (HP)
|
99% |
1254
21.6 IPS |
|
|
Machine Translation (Q)
|
98% |
1250
21.6 IPS |