| User | mattpippen |
| Upload Date | December 29 2025 03:22 AM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| Model | iPad mini (7th generation) |
| Model ID | iPad16,1 |
| Motherboard | J410AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.72 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1012
188.1 IPS |
|
|
Image Classification (HP)
|
100% |
1409
262.1 IPS |
|
|
Image Classification (Q)
|
94% |
1365
255.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
3517
57.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
3779
61.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
3664
59.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
11899
13.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
13467
15.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
13220
15.5 IPS |
|
|
Object Detection (SP)
|
100% |
1459
115.8 IPS |
|
|
Object Detection (HP)
|
100% |
1567
124.3 IPS |
|
|
Object Detection (Q)
|
90% |
1703
136.2 IPS |
|
|
Face Detection (SP)
|
100% |
5268
62.6 IPS |
|
|
Face Detection (HP)
|
100% |
7933
94.3 IPS |
|
|
Face Detection (Q)
|
100% |
6735
80.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
10133
78.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
11166
86.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
10066
78.8 IPS |
|
|
Style Transfer (SP)
|
100% |
25938
33.3 IPS |
|
|
Style Transfer (HP)
|
100% |
29114
37.4 IPS |
|
|
Style Transfer (Q)
|
96% |
29344
37.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3892
143.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3757
138.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3550
131.1 IPS |
|
|
Text Classification (SP)
|
100% |
3151
4.21 KIPS |
|
|
Text Classification (HP)
|
99% |
5557
7.42 KIPS |
|
|
Text Classification (Q)
|
93% |
5456
7.32 KIPS |
|
|
Machine Translation (SP)
|
100% |
1092
18.8 IPS |
|
|
Machine Translation (HP)
|
100% |
1249
21.5 IPS |
|
|
Machine Translation (Q)
|
98% |
1447
25.0 IPS |