| Upload Date | November 08 2025 03:28 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Air 13-inch (M2) |
| Model ID | iPad14,10 |
| Motherboard | J537AP |
| CPU Information | |
|---|---|
| Name | Apple M2 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.48 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1266
235.4 IPS |
|
|
Image Classification (HP)
|
100% |
2549
474.1 IPS |
|
|
Image Classification (Q)
|
96% |
1771
330.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1428
23.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2375
38.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
2743
44.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
6329
7.38 IPS |
|
|
Pose Estimation (HP)
|
100% |
15020
17.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
12823
15.0 IPS |
|
|
Object Detection (SP)
|
100% |
1413
112.1 IPS |
|
|
Object Detection (HP)
|
97% |
2816
224.2 IPS |
|
|
Object Detection (Q)
|
94% |
2039
162.5 IPS |
|
|
Face Detection (SP)
|
100% |
3060
36.4 IPS |
|
|
Face Detection (HP)
|
100% |
6013
71.4 IPS |
|
|
Face Detection (Q)
|
100% |
3477
41.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
5398
41.6 IPS |
|
|
Depth Estimation (HP)
|
98% |
10906
84.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
7653
59.8 IPS |
|
|
Style Transfer (SP)
|
100% |
18101
23.3 IPS |
|
|
Style Transfer (HP)
|
100% |
28212
36.3 IPS |
|
|
Style Transfer (Q)
|
96% |
23372
30.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3719
137.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4996
184.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3716
137.2 IPS |
|
|
Text Classification (SP)
|
100% |
2301
3.07 KIPS |
|
|
Text Classification (HP)
|
99% |
3887
5.19 KIPS |
|
|
Text Classification (Q)
|
93% |
3870
5.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
3647
62.8 IPS |
|
|
Machine Translation (HP)
|
98% |
6810
117.7 IPS |
|
|
Machine Translation (Q)
|
98% |
6825
117.9 IPS |