| User | harry34x |
| Upload Date | November 15 2025 12:04 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad17,1 |
| Model ID | iPad17,1 |
| Motherboard | J817AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.42 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 11.28 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2282
424.4 IPS |
|
|
Image Classification (HP)
|
100% |
3698
687.7 IPS |
|
|
Image Classification (Q)
|
96% |
2519
470.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
2384
38.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
3492
56.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
3816
61.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
11068
12.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
21030
24.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
17893
21.0 IPS |
|
|
Object Detection (SP)
|
100% |
2677
212.3 IPS |
|
|
Object Detection (HP)
|
97% |
4225
336.4 IPS |
|
|
Object Detection (Q)
|
94% |
2947
234.9 IPS |
|
|
Face Detection (SP)
|
100% |
4844
57.6 IPS |
|
|
Face Detection (HP)
|
100% |
8541
101.5 IPS |
|
|
Face Detection (Q)
|
100% |
4780
56.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
9151
70.5 IPS |
|
|
Depth Estimation (HP)
|
97% |
15271
118.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
10567
82.5 IPS |
|
|
Style Transfer (SP)
|
100% |
27291
35.1 IPS |
|
|
Style Transfer (HP)
|
100% |
41311
53.1 IPS |
|
|
Style Transfer (Q)
|
96% |
33814
43.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6024
222.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7319
270.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5207
192.3 IPS |
|
|
Text Classification (SP)
|
100% |
3052
4.07 KIPS |
|
|
Text Classification (HP)
|
99% |
5501
7.34 KIPS |
|
|
Text Classification (Q)
|
93% |
5566
7.47 KIPS |
|
|
Machine Translation (SP)
|
100% |
5288
91.1 IPS |
|
|
Machine Translation (HP)
|
98% |
9295
160.6 IPS |
|
|
Machine Translation (Q)
|
98% |
8836
152.7 IPS |