Upload Date | September 06 2025 06:22 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,10 |
Motherboard | J523AP |
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% |
1397
259.8 IPS |
|
Image Classification (HP)
|
100% |
5966
1.11 KIPS |
|
Image Classification (Q)
|
96% |
5923
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1368
22.2 IPS |
|
Image Segmentation (HP)
|
100% |
8908
144.4 IPS |
|
Image Segmentation (Q)
|
99% |
8218
133.2 IPS |
|
Pose Estimation (SP)
|
100% |
6049
7.06 IPS |
|
Pose Estimation (HP)
|
100% |
64918
75.7 IPS |
|
Pose Estimation (Q)
|
95% |
62121
72.8 IPS |
|
Object Detection (SP)
|
100% |
1066
84.6 IPS |
|
Object Detection (HP)
|
99% |
6313
502.2 IPS |
|
Object Detection (Q)
|
91% |
5877
469.6 IPS |
|
Face Detection (SP)
|
100% |
3028
36.0 IPS |
|
Face Detection (HP)
|
100% |
12237
145.4 IPS |
|
Face Detection (Q)
|
100% |
12517
148.7 IPS |
|
Depth Estimation (SP)
|
100% |
5664
43.6 IPS |
|
Depth Estimation (HP)
|
99% |
42296
325.9 IPS |
|
Depth Estimation (Q)
|
85% |
43412
339.2 IPS |
|
Style Transfer (SP)
|
100% |
16947
21.8 IPS |
|
Style Transfer (HP)
|
100% |
119175
153.2 IPS |
|
Style Transfer (Q)
|
96% |
112321
144.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3675
135.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
22942
847.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
22132
817.2 IPS |
|
Text Classification (SP)
|
100% |
2419
3.23 KIPS |
|
Text Classification (HP)
|
99% |
4164
5.56 KIPS |
|
Text Classification (Q)
|
93% |
4345
5.83 KIPS |
|
Machine Translation (SP)
|
100% |
2575
44.4 IPS |
|
Machine Translation (HP)
|
100% |
1465
25.2 IPS |
|
Machine Translation (Q)
|
98% |
1242
21.5 IPS |