| Upload Date | January 31 2026 02:33 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| 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% |
765
142.3 IPS |
|
|
Image Classification (HP)
|
100% |
17
3.08 IPS |
|
|
Image Classification (Q)
|
96% |
78
14.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
18
0.29 IPS |
|
|
Image Segmentation (HP)
|
100% |
21
0.34 IPS |
|
|
Image Segmentation (Q)
|
99% |
28
0.45 IPS |
|
|
Pose Estimation (SP)
|
100% |
101
0.12 IPS |
|
|
Pose Estimation (HP)
|
100% |
171
0.20 IPS |
|
|
Pose Estimation (Q)
|
96% |
145
0.17 IPS |
|
|
Object Detection (SP)
|
100% |
12
0.96 IPS |
|
|
Object Detection (HP)
|
100% |
14
1.15 IPS |
|
|
Object Detection (Q)
|
92% |
36
2.90 IPS |
|
|
Face Detection (SP)
|
100% |
49
0.58 IPS |
|
|
Face Detection (HP)
|
100% |
58
0.68 IPS |
|
|
Face Detection (Q)
|
100% |
85
1.00 IPS |
|
|
Depth Estimation (SP)
|
100% |
43
0.33 IPS |
|
|
Depth Estimation (HP)
|
99% |
62
0.48 IPS |
|
|
Depth Estimation (Q)
|
86% |
52
0.41 IPS |
|
|
Style Transfer (SP)
|
100% |
237
0.30 IPS |
|
|
Style Transfer (HP)
|
100% |
280
0.36 IPS |
|
|
Style Transfer (Q)
|
96% |
299
0.39 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
32
1.20 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
31
1.14 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
86
3.18 IPS |
|
|
Text Classification (SP)
|
100% |
2
3.27 IPS |
|
|
Text Classification (HP)
|
100% |
4
5.41 IPS |
|
|
Text Classification (Q)
|
93% |
84
113.4 IPS |
|
|
Machine Translation (SP)
|
100% |
492
8.47 IPS |
|
|
Machine Translation (HP)
|
100% |
477
8.22 IPS |
|
|
Machine Translation (Q)
|
98% |
477
8.24 IPS |