| User | M91 |
| Upload Date | March 21 2026 12:21 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
1637
304.4 IPS |
|
|
Image Classification (HP)
|
100% |
2904
540.1 IPS |
|
|
Image Classification (Q)
|
96% |
2029
379.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1582
25.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2384
38.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
3056
49.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
6839
7.98 IPS |
|
|
Pose Estimation (HP)
|
100% |
15128
17.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
13557
15.9 IPS |
|
|
Object Detection (SP)
|
100% |
1688
133.9 IPS |
|
|
Object Detection (HP)
|
97% |
3300
262.7 IPS |
|
|
Object Detection (Q)
|
94% |
2365
188.5 IPS |
|
|
Face Detection (SP)
|
100% |
3242
38.5 IPS |
|
|
Face Detection (HP)
|
100% |
6957
82.7 IPS |
|
|
Face Detection (Q)
|
100% |
3861
45.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
6534
50.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
12796
98.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
9003
70.4 IPS |
|
|
Style Transfer (SP)
|
100% |
19242
24.7 IPS |
|
|
Style Transfer (HP)
|
100% |
32745
42.1 IPS |
|
|
Style Transfer (Q)
|
96% |
27363
35.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4351
160.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5717
211.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4403
162.6 IPS |
|
|
Text Classification (SP)
|
99% |
5684
7.59 KIPS |
|
|
Text Classification (HP)
|
100% |
9856
13.2 KIPS |
|
|
Text Classification (Q)
|
92% |
9654
13.0 KIPS |
|
|
Machine Translation (SP)
|
100% |
3519
60.6 IPS |
|
|
Machine Translation (HP)
|
98% |
7288
125.9 IPS |
|
|
Machine Translation (Q)
|
98% |
7123
123.1 IPS |