| User | M91 |
| Upload Date | January 03 2026 01:51 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| 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% |
695
129.3 IPS |
|
|
Image Classification (HP)
|
100% |
856
159.2 IPS |
|
|
Image Classification (Q)
|
94% |
578
108.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
2386
38.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
2413
39.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
2303
37.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
9522
11.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
10195
11.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
9541
11.2 IPS |
|
|
Object Detection (SP)
|
100% |
959
76.1 IPS |
|
|
Object Detection (HP)
|
100% |
1097
87.0 IPS |
|
|
Object Detection (Q)
|
90% |
1001
80.1 IPS |
|
|
Face Detection (SP)
|
100% |
3662
43.5 IPS |
|
|
Face Detection (HP)
|
100% |
5542
65.8 IPS |
|
|
Face Detection (Q)
|
100% |
3393
40.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7246
55.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
7749
59.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
6355
49.7 IPS |
|
|
Style Transfer (SP)
|
100% |
17511
22.5 IPS |
|
|
Style Transfer (HP)
|
100% |
19303
24.8 IPS |
|
|
Style Transfer (Q)
|
96% |
19125
24.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2833
104.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2908
107.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2568
94.8 IPS |
|
|
Text Classification (SP)
|
100% |
2798
3.73 KIPS |
|
|
Text Classification (HP)
|
99% |
4775
6.37 KIPS |
|
|
Text Classification (Q)
|
93% |
4770
6.40 KIPS |
|
|
Machine Translation (SP)
|
100% |
685
11.8 IPS |
|
|
Machine Translation (HP)
|
100% |
722
12.4 IPS |
|
|
Machine Translation (Q)
|
98% |
766
13.2 IPS |