| Upload Date | November 25 2025 07:01 AM |
| Views | 2 |
| 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% |
2147
399.2 IPS |
|
|
Image Classification (HP)
|
100% |
3404
633.0 IPS |
|
|
Image Classification (Q)
|
96% |
2370
442.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2200
35.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
3266
53.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
3668
59.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
10046
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
19464
22.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
16760
19.6 IPS |
|
|
Object Detection (SP)
|
100% |
2484
197.0 IPS |
|
|
Object Detection (HP)
|
97% |
3834
305.2 IPS |
|
|
Object Detection (Q)
|
94% |
2760
220.0 IPS |
|
|
Face Detection (SP)
|
100% |
4390
52.2 IPS |
|
|
Face Detection (HP)
|
100% |
7875
93.6 IPS |
|
|
Face Detection (Q)
|
100% |
4575
54.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
8693
67.0 IPS |
|
|
Depth Estimation (HP)
|
97% |
14220
109.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
10086
78.7 IPS |
|
|
Style Transfer (SP)
|
100% |
24483
31.5 IPS |
|
|
Style Transfer (HP)
|
100% |
39076
50.2 IPS |
|
|
Style Transfer (Q)
|
96% |
32237
41.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6037
222.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7020
259.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4929
182.0 IPS |
|
|
Text Classification (SP)
|
100% |
3286
4.39 KIPS |
|
|
Text Classification (HP)
|
99% |
5802
7.74 KIPS |
|
|
Text Classification (Q)
|
93% |
5759
7.73 KIPS |
|
|
Machine Translation (SP)
|
100% |
4583
78.9 IPS |
|
|
Machine Translation (HP)
|
98% |
8103
140.0 IPS |
|
|
Machine Translation (Q)
|
98% |
8034
138.8 IPS |