Upload Date | September 16 2025 01:35 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% |
1416
263.4 IPS |
|
Image Classification (HP)
|
100% |
6278
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5927
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1366
22.2 IPS |
|
Image Segmentation (HP)
|
100% |
9672
156.8 IPS |
|
Image Segmentation (Q)
|
99% |
9992
162.0 IPS |
|
Pose Estimation (SP)
|
100% |
6519
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
68716
80.2 IPS |
|
Pose Estimation (Q)
|
95% |
66297
77.7 IPS |
|
Object Detection (SP)
|
100% |
1508
119.6 IPS |
|
Object Detection (HP)
|
99% |
7242
576.1 IPS |
|
Object Detection (Q)
|
91% |
6710
536.1 IPS |
|
Face Detection (SP)
|
100% |
3033
36.0 IPS |
|
Face Detection (HP)
|
100% |
16430
195.2 IPS |
|
Face Detection (Q)
|
100% |
15084
179.2 IPS |
|
Depth Estimation (SP)
|
100% |
5690
43.8 IPS |
|
Depth Estimation (HP)
|
99% |
47238
363.9 IPS |
|
Depth Estimation (Q)
|
85% |
47704
372.8 IPS |
|
Style Transfer (SP)
|
100% |
16970
21.8 IPS |
|
Style Transfer (HP)
|
100% |
119772
154.0 IPS |
|
Style Transfer (Q)
|
96% |
114895
148.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3691
136.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
23222
857.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
23619
872.2 IPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3987
5.32 KIPS |
|
Text Classification (Q)
|
93% |
3961
5.32 KIPS |
|
Machine Translation (SP)
|
100% |
2482
42.8 IPS |
|
Machine Translation (HP)
|
100% |
3567
61.4 IPS |
|
Machine Translation (Q)
|
98% |
3658
63.2 IPS |