| Upload Date | October 21 2025 01:02 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.0.1 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,8 |
| Motherboard | J522AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.34 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1313
244.2 IPS |
|
|
Image Classification (HP)
|
100% |
6004
1.12 KIPS |
|
|
Image Classification (Q)
|
96% |
5605
1.05 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1344
21.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
9046
146.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
9348
151.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
6023
7.03 IPS |
|
|
Pose Estimation (HP)
|
100% |
67451
78.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
64534
75.6 IPS |
|
|
Object Detection (SP)
|
100% |
1390
110.2 IPS |
|
|
Object Detection (HP)
|
99% |
6919
550.4 IPS |
|
|
Object Detection (Q)
|
91% |
6494
518.9 IPS |
|
|
Face Detection (SP)
|
100% |
2988
35.5 IPS |
|
|
Face Detection (HP)
|
100% |
13923
165.4 IPS |
|
|
Face Detection (Q)
|
100% |
12881
153.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
5483
42.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
43887
338.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
44134
344.9 IPS |
|
|
Style Transfer (SP)
|
100% |
16517
21.2 IPS |
|
|
Style Transfer (HP)
|
100% |
120494
154.9 IPS |
|
|
Style Transfer (Q)
|
96% |
113206
146.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3521
130.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
23886
882.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
23055
851.3 IPS |
|
|
Text Classification (SP)
|
100% |
2449
3.27 KIPS |
|
|
Text Classification (HP)
|
99% |
4373
5.84 KIPS |
|
|
Text Classification (Q)
|
93% |
4334
5.82 KIPS |
|
|
Machine Translation (SP)
|
100% |
2522
43.4 IPS |
|
|
Machine Translation (HP)
|
100% |
2694
46.4 IPS |
|
|
Machine Translation (Q)
|
98% |
2787
48.2 IPS |