| User | markerichannelly |
| Upload Date | July 16 2025 03:30 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 18.5 |
| 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% |
4464
830.1 IPS |
|
|
Image Classification (HP)
|
100% |
4771
887.2 IPS |
|
|
Image Classification (Q)
|
96% |
4501
840.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
7199
116.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
7900
128.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
7614
123.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
28102
32.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
29754
34.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
29446
34.5 IPS |
|
|
Object Detection (SP)
|
100% |
4589
364.0 IPS |
|
|
Object Detection (HP)
|
100% |
5161
409.4 IPS |
|
|
Object Detection (Q)
|
92% |
4757
379.7 IPS |
|
|
Face Detection (SP)
|
100% |
12813
152.2 IPS |
|
|
Face Detection (HP)
|
100% |
16681
198.2 IPS |
|
|
Face Detection (Q)
|
100% |
13415
159.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
20359
156.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
21912
168.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
20225
158.0 IPS |
|
|
Style Transfer (SP)
|
100% |
57393
73.8 IPS |
|
|
Style Transfer (HP)
|
100% |
66429
85.4 IPS |
|
|
Style Transfer (Q)
|
96% |
64780
83.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11612
428.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
11436
422.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10336
381.7 IPS |
|
|
Text Classification (SP)
|
100% |
2897
3.87 KIPS |
|
|
Text Classification (HP)
|
100% |
5536
7.39 KIPS |
|
|
Text Classification (Q)
|
93% |
5680
7.62 KIPS |
|
|
Machine Translation (SP)
|
100% |
3026
52.1 IPS |
|
|
Machine Translation (HP)
|
100% |
3509
60.4 IPS |
|
|
Machine Translation (Q)
|
98% |
2760
47.7 IPS |