| Upload Date | November 12 2025 09:53 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.2 |
| 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% |
484
90.1 IPS |
|
|
Image Classification (HP)
|
100% |
806
150.0 IPS |
|
|
Image Classification (Q)
|
96% |
644
120.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
611
9.91 IPS |
|
|
Image Segmentation (HP)
|
100% |
982
15.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1023
16.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2484
2.90 IPS |
|
|
Pose Estimation (HP)
|
100% |
2170
2.53 IPS |
|
|
Pose Estimation (Q)
|
96% |
1999
2.34 IPS |
|
|
Object Detection (SP)
|
100% |
540
42.8 IPS |
|
|
Object Detection (HP)
|
99% |
967
76.7 IPS |
|
|
Object Detection (Q)
|
92% |
769
61.4 IPS |
|
|
Face Detection (SP)
|
100% |
1256
14.9 IPS |
|
|
Face Detection (HP)
|
100% |
2312
27.5 IPS |
|
|
Face Detection (Q)
|
100% |
1478
17.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
1647
12.7 IPS |
|
|
Depth Estimation (HP)
|
98% |
2654
20.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
2221
17.4 IPS |
|
|
Style Transfer (SP)
|
100% |
4406
5.66 IPS |
|
|
Style Transfer (HP)
|
100% |
7344
9.44 IPS |
|
|
Style Transfer (Q)
|
96% |
6557
8.46 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1236
45.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1406
51.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1183
43.7 IPS |
|
|
Text Classification (SP)
|
100% |
287
383.4 IPS |
|
|
Text Classification (HP)
|
100% |
557
744.0 IPS |
|
|
Text Classification (Q)
|
93% |
555
744.8 IPS |
|
|
Machine Translation (SP)
|
100% |
716
12.3 IPS |
|
|
Machine Translation (HP)
|
98% |
1247
21.6 IPS |
|
|
Machine Translation (Q)
|
98% |
1256
21.7 IPS |