| User | M91 |
| Upload Date | March 25 2026 08:26 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A16 |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
739
137.4 IPS |
|
|
Image Classification (HP)
|
100% |
642
119.4 IPS |
|
|
Image Classification (Q)
|
94% |
931
174.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
2370
38.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
2415
39.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
2346
38.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
9475
11.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
10290
12.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
9676
11.3 IPS |
|
|
Object Detection (SP)
|
100% |
1030
81.7 IPS |
|
|
Object Detection (HP)
|
100% |
983
78.0 IPS |
|
|
Object Detection (Q)
|
91% |
781
62.5 IPS |
|
|
Face Detection (SP)
|
100% |
3728
44.3 IPS |
|
|
Face Detection (HP)
|
100% |
5484
65.2 IPS |
|
|
Face Detection (Q)
|
100% |
4392
52.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
7699
59.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
8089
62.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
7096
55.5 IPS |
|
|
Style Transfer (SP)
|
100% |
17634
22.7 IPS |
|
|
Style Transfer (HP)
|
100% |
19559
25.1 IPS |
|
|
Style Transfer (Q)
|
96% |
19089
24.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2853
105.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2936
108.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2539
93.7 IPS |
|
|
Text Classification (SP)
|
100% |
5154
6.88 KIPS |
|
|
Text Classification (HP)
|
99% |
8354
11.2 KIPS |
|
|
Text Classification (Q)
|
93% |
8401
11.3 KIPS |
|
|
Machine Translation (SP)
|
100% |
981
16.9 IPS |
|
|
Machine Translation (HP)
|
100% |
938
16.2 IPS |
|
|
Machine Translation (Q)
|
98% |
819
14.2 IPS |