| Upload Date | November 23 2025 02:49 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 | iPad8,8 |
| Motherboard | J321xAP |
| 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 | 5.53 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
485
90.2 IPS |
|
|
Image Classification (HP)
|
100% |
792
147.4 IPS |
|
|
Image Classification (Q)
|
96% |
634
118.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
612
9.92 IPS |
|
|
Image Segmentation (HP)
|
100% |
960
15.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
1008
16.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
2673
3.12 IPS |
|
|
Pose Estimation (HP)
|
100% |
2368
2.76 IPS |
|
|
Pose Estimation (Q)
|
96% |
1957
2.29 IPS |
|
|
Object Detection (SP)
|
100% |
550
43.6 IPS |
|
|
Object Detection (HP)
|
99% |
944
74.9 IPS |
|
|
Object Detection (Q)
|
92% |
756
60.3 IPS |
|
|
Face Detection (SP)
|
100% |
1257
14.9 IPS |
|
|
Face Detection (HP)
|
100% |
2341
27.8 IPS |
|
|
Face Detection (Q)
|
100% |
1494
17.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
1764
13.6 IPS |
|
|
Depth Estimation (HP)
|
98% |
2697
20.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
2234
17.5 IPS |
|
|
Style Transfer (SP)
|
100% |
5161
6.63 IPS |
|
|
Style Transfer (HP)
|
100% |
7980
10.3 IPS |
|
|
Style Transfer (Q)
|
96% |
7139
9.21 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1261
46.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1518
56.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1229
45.4 IPS |
|
|
Text Classification (SP)
|
100% |
291
388.3 IPS |
|
|
Text Classification (HP)
|
100% |
565
754.1 IPS |
|
|
Text Classification (Q)
|
93% |
556
746.2 IPS |
|
|
Machine Translation (SP)
|
100% |
723
12.5 IPS |
|
|
Machine Translation (HP)
|
99% |
1265
21.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1269
21.9 IPS |