Upload Date | September 16 2025 01:40 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,9 |
Motherboard | J522xAP |
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 | 15.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1411
262.4 IPS |
|
Image Classification (HP)
|
100% |
6194
1.15 KIPS |
|
Image Classification (Q)
|
96% |
5885
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1358
22.0 IPS |
|
Image Segmentation (HP)
|
100% |
9657
156.5 IPS |
|
Image Segmentation (Q)
|
99% |
10022
162.5 IPS |
|
Pose Estimation (SP)
|
100% |
6507
7.59 IPS |
|
Pose Estimation (HP)
|
100% |
68806
80.3 IPS |
|
Pose Estimation (Q)
|
95% |
66711
78.2 IPS |
|
Object Detection (SP)
|
100% |
1495
118.5 IPS |
|
Object Detection (HP)
|
99% |
7211
573.6 IPS |
|
Object Detection (Q)
|
91% |
6712
536.3 IPS |
|
Face Detection (SP)
|
100% |
3037
36.1 IPS |
|
Face Detection (HP)
|
100% |
16423
195.1 IPS |
|
Face Detection (Q)
|
100% |
15181
180.4 IPS |
|
Depth Estimation (SP)
|
100% |
5627
43.3 IPS |
|
Depth Estimation (HP)
|
99% |
47244
364.0 IPS |
|
Depth Estimation (Q)
|
85% |
47690
372.7 IPS |
|
Style Transfer (SP)
|
100% |
16979
21.8 IPS |
|
Style Transfer (HP)
|
100% |
120142
154.4 IPS |
|
Style Transfer (Q)
|
96% |
114879
148.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3687
136.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
23086
852.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
23977
885.4 IPS |
|
Text Classification (SP)
|
100% |
2298
3.07 KIPS |
|
Text Classification (HP)
|
100% |
3993
5.33 KIPS |
|
Text Classification (Q)
|
93% |
3966
5.32 KIPS |
|
Machine Translation (SP)
|
100% |
2471
42.6 IPS |
|
Machine Translation (HP)
|
100% |
3569
61.5 IPS |
|
Machine Translation (Q)
|
98% |
3640
62.9 IPS |