User | pakitt |
Upload Date | August 03 2025 12:42 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPad Air 11-inch (M2) |
Model ID | iPad14,8 |
Motherboard | J507AP |
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 | 7.46 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1380
256.6 IPS |
|
Image Classification (HP)
|
100% |
14932
2.78 KIPS |
|
Image Classification (Q)
|
96% |
15387
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1471
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
19579
317.4 IPS |
|
Image Segmentation (Q)
|
99% |
24171
391.8 IPS |
|
Pose Estimation (SP)
|
100% |
6830
7.97 IPS |
|
Pose Estimation (HP)
|
100% |
105276
122.8 IPS |
|
Pose Estimation (Q)
|
95% |
105305
123.4 IPS |
|
Object Detection (SP)
|
100% |
1538
122.0 IPS |
|
Object Detection (HP)
|
99% |
15736
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17042
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3127
37.2 IPS |
|
Face Detection (HP)
|
100% |
33815
401.8 IPS |
|
Face Detection (Q)
|
100% |
42219
501.7 IPS |
|
Depth Estimation (SP)
|
100% |
5587
43.0 IPS |
|
Depth Estimation (HP)
|
99% |
87655
675.3 IPS |
|
Depth Estimation (Q)
|
85% |
108814
850.3 IPS |
|
Style Transfer (SP)
|
100% |
18704
24.0 IPS |
|
Style Transfer (HP)
|
100% |
205017
263.6 IPS |
|
Style Transfer (Q)
|
96% |
194603
251.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3996
147.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
37361
1.38 KIPS |
|
Image Super-Resolution (Q)
|
99% |
44150
1.63 KIPS |
|
Text Classification (SP)
|
100% |
2307
3.08 KIPS |
|
Text Classification (HP)
|
99% |
3888
5.19 KIPS |
|
Text Classification (Q)
|
93% |
3861
5.18 KIPS |
|
Machine Translation (SP)
|
100% |
3879
66.8 IPS |
|
Machine Translation (HP)
|
100% |
4269
73.5 IPS |
|
Machine Translation (Q)
|
98% |
4408
76.2 IPS |