Upload Date | September 16 2025 11:02 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPad Air (4th generation) |
Model ID | iPad13,1 |
Motherboard | J307AP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.78 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1176
218.6 IPS |
|
Image Classification (HP)
|
100% |
4879
907.4 IPS |
|
Image Classification (Q)
|
96% |
5117
955.6 IPS |
|
Image Segmentation (SP)
|
100% |
1040
16.9 IPS |
|
Image Segmentation (HP)
|
100% |
7991
129.5 IPS |
|
Image Segmentation (Q)
|
99% |
7679
124.5 IPS |
|
Pose Estimation (SP)
|
100% |
5065
5.91 IPS |
|
Pose Estimation (HP)
|
100% |
58751
68.6 IPS |
|
Pose Estimation (Q)
|
95% |
57834
67.8 IPS |
|
Object Detection (SP)
|
100% |
1227
97.3 IPS |
|
Object Detection (HP)
|
99% |
5958
474.0 IPS |
|
Object Detection (Q)
|
91% |
5359
428.2 IPS |
|
Face Detection (SP)
|
100% |
2451
29.1 IPS |
|
Face Detection (HP)
|
100% |
12794
152.0 IPS |
|
Face Detection (Q)
|
100% |
10850
128.9 IPS |
|
Depth Estimation (SP)
|
100% |
4745
36.6 IPS |
|
Depth Estimation (HP)
|
99% |
38310
295.2 IPS |
|
Depth Estimation (Q)
|
85% |
36919
288.5 IPS |
|
Style Transfer (SP)
|
100% |
14062
18.1 IPS |
|
Style Transfer (HP)
|
100% |
107300
137.9 IPS |
|
Style Transfer (Q)
|
96% |
99703
128.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
2796
103.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
21166
781.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
18477
682.3 IPS |
|
Text Classification (SP)
|
100% |
2329
3.11 KIPS |
|
Text Classification (HP)
|
100% |
2626
3.50 KIPS |
|
Text Classification (Q)
|
93% |
2568
3.45 KIPS |
|
Machine Translation (SP)
|
100% |
2262
39.0 IPS |
|
Machine Translation (HP)
|
100% |
4083
70.3 IPS |
|
Machine Translation (Q)
|
98% |
4426
76.5 IPS |