| Upload Date | November 21 2026 11:37 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 27.2.1 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,1 |
| Motherboard | J310AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.92 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.77 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
728
135.4 IPS |
|
|
Image Classification (HP)
|
100% |
653
121.5 IPS |
|
|
Image Classification (Q)
|
94% |
619
115.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2665
43.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2856
46.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
2664
43.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
10915
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
12151
14.2 IPS |
|
|
Pose Estimation (Q)
|
96% |
11835
13.9 IPS |
|
|
Object Detection (SP)
|
100% |
1205
95.6 IPS |
|
|
Object Detection (HP)
|
100% |
1077
85.4 IPS |
|
|
Object Detection (Q)
|
91% |
1070
85.6 IPS |
|
|
Face Detection (SP)
|
100% |
4326
51.4 IPS |
|
|
Face Detection (HP)
|
100% |
4287
50.9 IPS |
|
|
Face Detection (Q)
|
100% |
4317
51.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7181
55.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
7591
58.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
6976
54.5 IPS |
|
|
Style Transfer (SP)
|
100% |
18097
23.3 IPS |
|
|
Style Transfer (HP)
|
100% |
22241
28.6 IPS |
|
|
Style Transfer (Q)
|
96% |
21344
27.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2693
99.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2805
103.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2540
93.8 IPS |
|
|
Text Classification (SP)
|
100% |
4470
5.97 KIPS |
|
|
Text Classification (HP)
|
99% |
7225
9.64 KIPS |
|
|
Text Classification (Q)
|
93% |
7224
9.70 KIPS |
|
|
Machine Translation (SP)
|
100% |
900
15.5 IPS |
|
|
Machine Translation (HP)
|
100% |
1023
17.6 IPS |
|
|
Machine Translation (Q)
|
98% |
997
17.2 IPS |