| Upload Date | November 09 2025 11:56 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,3 |
| Motherboard | J318AP |
| 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% |
486
90.3 IPS |
|
|
Image Classification (HP)
|
100% |
793
147.5 IPS |
|
|
Image Classification (Q)
|
96% |
621
116.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
610
9.88 IPS |
|
|
Image Segmentation (HP)
|
100% |
958
15.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
1015
16.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
2611
3.05 IPS |
|
|
Pose Estimation (HP)
|
100% |
2304
2.69 IPS |
|
|
Pose Estimation (Q)
|
96% |
2144
2.51 IPS |
|
|
Object Detection (SP)
|
100% |
542
43.0 IPS |
|
|
Object Detection (HP)
|
99% |
944
74.9 IPS |
|
|
Object Detection (Q)
|
92% |
754
60.2 IPS |
|
|
Face Detection (SP)
|
100% |
1256
14.9 IPS |
|
|
Face Detection (HP)
|
100% |
2313
27.5 IPS |
|
|
Face Detection (Q)
|
100% |
1477
17.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
1757
13.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
2675
20.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
2220
17.4 IPS |
|
|
Style Transfer (SP)
|
100% |
5061
6.51 IPS |
|
|
Style Transfer (HP)
|
100% |
7845
10.1 IPS |
|
|
Style Transfer (Q)
|
96% |
7025
9.07 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1231
45.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1441
53.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1194
44.1 IPS |
|
|
Text Classification (SP)
|
100% |
286
382.2 IPS |
|
|
Text Classification (HP)
|
100% |
548
731.1 IPS |
|
|
Text Classification (Q)
|
93% |
544
730.1 IPS |
|
|
Machine Translation (SP)
|
100% |
723
12.5 IPS |
|
|
Machine Translation (HP)
|
99% |
1301
22.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1255
21.7 IPS |