| Upload Date | November 06 2025 09:19 PM |
| 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% |
2126
395.4 IPS |
|
|
Image Classification (HP)
|
100% |
3389
630.2 IPS |
|
|
Image Classification (Q)
|
96% |
2375
443.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2190
35.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
3314
53.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
3626
58.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
10031
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
19512
22.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
16701
19.6 IPS |
|
|
Object Detection (SP)
|
100% |
2469
195.8 IPS |
|
|
Object Detection (HP)
|
97% |
3839
305.6 IPS |
|
|
Object Detection (Q)
|
94% |
2768
220.6 IPS |
|
|
Face Detection (SP)
|
100% |
4350
51.7 IPS |
|
|
Face Detection (HP)
|
100% |
7822
92.9 IPS |
|
|
Face Detection (Q)
|
100% |
4506
53.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
8614
66.4 IPS |
|
|
Depth Estimation (HP)
|
97% |
14145
109.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
10013
78.2 IPS |
|
|
Style Transfer (SP)
|
100% |
24464
31.4 IPS |
|
|
Style Transfer (HP)
|
100% |
38837
49.9 IPS |
|
|
Style Transfer (Q)
|
96% |
31995
41.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6100
225.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7013
258.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4963
183.3 IPS |
|
|
Text Classification (SP)
|
100% |
3351
4.47 KIPS |
|
|
Text Classification (HP)
|
99% |
5893
7.87 KIPS |
|
|
Text Classification (Q)
|
93% |
5720
7.68 KIPS |
|
|
Machine Translation (SP)
|
100% |
4587
79.0 IPS |
|
|
Machine Translation (HP)
|
98% |
8150
140.8 IPS |
|
|
Machine Translation (Q)
|
98% |
8175
141.3 IPS |