| User | M91 |
| Upload Date | April 01 2026 09:06 AM |
| Views | 20 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| Model | iPad (11th generation) |
| Model ID | iPad15,7 |
| Motherboard | J481AP |
| CPU Information | |
|---|---|
| Name | Apple A16 |
| Topology | 1 Processor, 5 Cores |
| Identifier | ARM |
| Base Frequency | 3.44 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 5.78 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
530
98.6 IPS |
|
|
Image Classification (HP)
|
100% |
508
94.4 IPS |
|
|
Image Classification (Q)
|
94% |
934
174.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2425
39.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
2317
37.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
2372
38.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
9478
11.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
10329
12.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
9806
11.5 IPS |
|
|
Object Detection (SP)
|
100% |
992
78.7 IPS |
|
|
Object Detection (HP)
|
100% |
977
77.5 IPS |
|
|
Object Detection (Q)
|
91% |
828
66.2 IPS |
|
|
Face Detection (SP)
|
100% |
3508
41.7 IPS |
|
|
Face Detection (HP)
|
100% |
4033
47.9 IPS |
|
|
Face Detection (Q)
|
100% |
5054
60.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
6690
51.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
7790
60.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
6174
48.3 IPS |
|
|
Style Transfer (SP)
|
100% |
17598
22.6 IPS |
|
|
Style Transfer (HP)
|
100% |
19568
25.2 IPS |
|
|
Style Transfer (Q)
|
96% |
19061
24.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2838
104.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2822
104.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2500
92.3 IPS |
|
|
Text Classification (SP)
|
99% |
5208
6.95 KIPS |
|
|
Text Classification (HP)
|
99% |
8283
11.1 KIPS |
|
|
Text Classification (Q)
|
93% |
8249
11.1 KIPS |
|
|
Machine Translation (SP)
|
100% |
880
15.2 IPS |
|
|
Machine Translation (HP)
|
100% |
941
16.2 IPS |
|
|
Machine Translation (Q)
|
98% |
994
17.2 IPS |