| Upload Date | November 10 2025 06:53 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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% |
334
62.1 IPS |
|
|
Image Classification (HP)
|
100% |
2121
394.4 IPS |
|
|
Image Classification (Q)
|
99% |
156
29.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
300
4.86 IPS |
|
|
Image Segmentation (HP)
|
100% |
364
5.90 IPS |
|
|
Image Segmentation (Q)
|
99% |
224
3.63 IPS |
|
|
Pose Estimation (SP)
|
100% |
2136
2.49 IPS |
|
|
Pose Estimation (HP)
|
100% |
27265
31.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
1505
1.76 IPS |
|
|
Object Detection (SP)
|
100% |
379
30.1 IPS |
|
|
Object Detection (HP)
|
100% |
1367
108.4 IPS |
|
|
Object Detection (Q)
|
94% |
192
15.3 IPS |
|
|
Face Detection (SP)
|
100% |
843
10.0 IPS |
|
|
Face Detection (HP)
|
100% |
6457
76.7 IPS |
|
|
Face Detection (Q)
|
100% |
300
3.57 IPS |
|
|
Depth Estimation (SP)
|
100% |
1039
8.01 IPS |
|
|
Depth Estimation (HP)
|
99% |
22948
176.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
604
4.71 IPS |
|
|
Style Transfer (SP)
|
100% |
3537
4.55 IPS |
|
|
Style Transfer (HP)
|
100% |
3300
4.24 IPS |
|
|
Style Transfer (Q)
|
96% |
2522
3.25 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
947
35.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3248
119.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
466
17.2 IPS |
|
|
Text Classification (SP)
|
100% |
257
343.0 IPS |
|
|
Text Classification (HP)
|
100% |
297
396.2 IPS |
|
|
Text Classification (Q)
|
93% |
296
397.8 IPS |
|
|
Machine Translation (SP)
|
100% |
488
8.40 IPS |
|
|
Machine Translation (HP)
|
100% |
375
6.46 IPS |
|
|
Machine Translation (Q)
|
98% |
374
6.46 IPS |