Upload Date | September 30 2025 01:14 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 26.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,11 |
Motherboard | J523xAP |
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 | 15.34 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1298
241.4 IPS |
|
Image Classification (HP)
|
100% |
6116
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5425
1.01 KIPS |
|
Image Segmentation (SP)
|
100% |
1311
21.3 IPS |
|
Image Segmentation (HP)
|
100% |
8794
142.6 IPS |
|
Image Segmentation (Q)
|
99% |
9111
147.7 IPS |
|
Pose Estimation (SP)
|
100% |
5990
6.99 IPS |
|
Pose Estimation (HP)
|
100% |
67042
78.2 IPS |
|
Pose Estimation (Q)
|
95% |
64119
75.2 IPS |
|
Object Detection (SP)
|
100% |
1381
109.5 IPS |
|
Object Detection (HP)
|
99% |
6386
508.0 IPS |
|
Object Detection (Q)
|
91% |
5957
476.0 IPS |
|
Face Detection (SP)
|
100% |
2964
35.2 IPS |
|
Face Detection (HP)
|
100% |
11937
141.8 IPS |
|
Face Detection (Q)
|
100% |
11391
135.4 IPS |
|
Depth Estimation (SP)
|
100% |
5424
41.8 IPS |
|
Depth Estimation (HP)
|
99% |
44505
342.9 IPS |
|
Depth Estimation (Q)
|
85% |
41202
322.0 IPS |
|
Style Transfer (SP)
|
100% |
16457
21.2 IPS |
|
Style Transfer (HP)
|
100% |
118851
152.8 IPS |
|
Style Transfer (Q)
|
96% |
111883
144.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3462
127.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
24310
897.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
22337
824.8 IPS |
|
Text Classification (SP)
|
100% |
2413
3.22 KIPS |
|
Text Classification (HP)
|
99% |
4271
5.70 KIPS |
|
Text Classification (Q)
|
93% |
4298
5.77 KIPS |
|
Machine Translation (SP)
|
100% |
2482
42.7 IPS |
|
Machine Translation (HP)
|
100% |
2336
40.2 IPS |
|
Machine Translation (Q)
|
98% |
2398
41.4 IPS |