Upload Date | September 16 2025 01:54 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.36 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1280
238.0 IPS |
|
Image Classification (HP)
|
100% |
14307
2.66 KIPS |
|
Image Classification (Q)
|
96% |
16232
3.03 KIPS |
|
Image Segmentation (SP)
|
100% |
1440
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
19540
316.8 IPS |
|
Image Segmentation (Q)
|
99% |
23556
381.9 IPS |
|
Pose Estimation (SP)
|
100% |
6262
7.31 IPS |
|
Pose Estimation (HP)
|
100% |
104988
122.5 IPS |
|
Pose Estimation (Q)
|
95% |
105965
124.2 IPS |
|
Object Detection (SP)
|
100% |
1400
111.0 IPS |
|
Object Detection (HP)
|
99% |
15672
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17356
1.39 KIPS |
|
Face Detection (SP)
|
100% |
2975
35.4 IPS |
|
Face Detection (HP)
|
100% |
33386
396.7 IPS |
|
Face Detection (Q)
|
100% |
42877
509.5 IPS |
|
Depth Estimation (SP)
|
100% |
5417
41.7 IPS |
|
Depth Estimation (HP)
|
99% |
86446
666.0 IPS |
|
Depth Estimation (Q)
|
85% |
107490
840.0 IPS |
|
Style Transfer (SP)
|
100% |
17806
22.9 IPS |
|
Style Transfer (HP)
|
100% |
202912
260.8 IPS |
|
Style Transfer (Q)
|
96% |
194510
251.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3821
141.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
41160
1.52 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49437
1.83 KIPS |
|
Text Classification (SP)
|
100% |
2318
3.09 KIPS |
|
Text Classification (HP)
|
99% |
3916
5.23 KIPS |
|
Text Classification (Q)
|
93% |
3898
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
3573
61.5 IPS |
|
Machine Translation (HP)
|
100% |
4122
71.0 IPS |
|
Machine Translation (Q)
|
98% |
4308
74.4 IPS |