| Upload Date | October 27 2025 09:50 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro 11-inch (M4) |
| Model ID | iPad16,3 |
| Motherboard | J717AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.29 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2129
396.0 IPS |
|
|
Image Classification (HP)
|
100% |
3407
633.5 IPS |
|
|
Image Classification (Q)
|
96% |
2361
440.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
2202
35.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
3249
52.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
3638
59.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
10027
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
19407
22.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
16713
19.6 IPS |
|
|
Object Detection (SP)
|
100% |
2485
197.1 IPS |
|
|
Object Detection (HP)
|
97% |
3844
306.0 IPS |
|
|
Object Detection (Q)
|
94% |
2776
221.3 IPS |
|
|
Face Detection (SP)
|
100% |
4375
52.0 IPS |
|
|
Face Detection (HP)
|
100% |
7772
92.4 IPS |
|
|
Face Detection (Q)
|
100% |
4536
53.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
8640
66.6 IPS |
|
|
Depth Estimation (HP)
|
97% |
14224
110.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
10044
78.4 IPS |
|
|
Style Transfer (SP)
|
100% |
24203
31.1 IPS |
|
|
Style Transfer (HP)
|
100% |
39007
50.1 IPS |
|
|
Style Transfer (Q)
|
96% |
32142
41.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6058
223.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7000
258.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4936
182.3 IPS |
|
|
Text Classification (SP)
|
100% |
3232
4.31 KIPS |
|
|
Text Classification (HP)
|
99% |
5937
7.92 KIPS |
|
|
Text Classification (Q)
|
93% |
5854
7.86 KIPS |
|
|
Machine Translation (SP)
|
100% |
4597
79.2 IPS |
|
|
Machine Translation (HP)
|
98% |
8089
139.8 IPS |
|
|
Machine Translation (Q)
|
98% |
8130
140.5 IPS |