| Upload Date | October 21 2025 12:56 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% |
1138
211.7 IPS |
|
|
Image Classification (HP)
|
100% |
6143
1.14 KIPS |
|
|
Image Classification (Q)
|
96% |
5851
1.09 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1111
18.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
6599
107.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
8789
142.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
3338
3.90 IPS |
|
|
Pose Estimation (HP)
|
100% |
65810
76.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
64420
75.5 IPS |
|
|
Object Detection (SP)
|
100% |
1363
108.1 IPS |
|
|
Object Detection (HP)
|
99% |
6978
555.1 IPS |
|
|
Object Detection (Q)
|
91% |
5782
462.0 IPS |
|
|
Face Detection (SP)
|
100% |
2921
34.7 IPS |
|
|
Face Detection (HP)
|
100% |
12388
147.2 IPS |
|
|
Face Detection (Q)
|
100% |
11429
135.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
4913
37.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
42221
325.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
44370
346.7 IPS |
|
|
Style Transfer (SP)
|
100% |
15151
19.5 IPS |
|
|
Style Transfer (HP)
|
100% |
118186
151.9 IPS |
|
|
Style Transfer (Q)
|
96% |
111571
144.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3504
129.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
23281
859.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
24013
886.7 IPS |
|
|
Text Classification (SP)
|
100% |
2459
3.28 KIPS |
|
|
Text Classification (HP)
|
99% |
4352
5.81 KIPS |
|
|
Text Classification (Q)
|
93% |
4320
5.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
2487
42.8 IPS |
|
|
Machine Translation (HP)
|
100% |
2527
43.5 IPS |
|
|
Machine Translation (Q)
|
98% |
2425
41.9 IPS |