| Upload Date | November 09 2025 10:14 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
907
168.7 IPS |
|
|
Image Classification (HP)
|
100% |
1206
224.4 IPS |
|
|
Image Classification (Q)
|
96% |
152
28.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
358
5.81 IPS |
|
|
Image Segmentation (HP)
|
100% |
373
6.05 IPS |
|
|
Image Segmentation (Q)
|
99% |
219
3.55 IPS |
|
|
Pose Estimation (SP)
|
100% |
2812
3.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
3982
4.65 IPS |
|
|
Pose Estimation (Q)
|
96% |
1701
1.99 IPS |
|
|
Object Detection (SP)
|
100% |
901
71.5 IPS |
|
|
Object Detection (HP)
|
100% |
1234
97.9 IPS |
|
|
Object Detection (Q)
|
92% |
177
14.1 IPS |
|
|
Face Detection (SP)
|
100% |
3386
40.2 IPS |
|
|
Face Detection (HP)
|
100% |
3860
45.9 IPS |
|
|
Face Detection (Q)
|
100% |
294
3.49 IPS |
|
|
Depth Estimation (SP)
|
100% |
2858
22.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4059
31.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
532
4.16 IPS |
|
|
Style Transfer (SP)
|
100% |
7893
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9597
12.3 IPS |
|
|
Style Transfer (Q)
|
96% |
2995
3.86 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1347
49.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1810
66.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
390
14.4 IPS |
|
|
Text Classification (SP)
|
100% |
94
125.4 IPS |
|
|
Text Classification (HP)
|
100% |
102
136.0 IPS |
|
|
Text Classification (Q)
|
93% |
105
141.5 IPS |
|
|
Machine Translation (SP)
|
100% |
526
9.06 IPS |
|
|
Machine Translation (HP)
|
100% |
470
8.10 IPS |
|
|
Machine Translation (Q)
|
98% |
471
8.14 IPS |