Upload Date | August 27 2025 01:42 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1385
257.6 IPS |
|
Image Classification (HP)
|
100% |
14301
2.66 KIPS |
|
Image Classification (Q)
|
96% |
14962
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1525
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
19645
318.5 IPS |
|
Image Segmentation (Q)
|
99% |
24035
389.6 IPS |
|
Pose Estimation (SP)
|
100% |
6854
8.00 IPS |
|
Pose Estimation (HP)
|
100% |
105529
123.1 IPS |
|
Pose Estimation (Q)
|
95% |
105283
123.4 IPS |
|
Object Detection (SP)
|
100% |
1545
122.5 IPS |
|
Object Detection (HP)
|
99% |
15033
1.20 KIPS |
|
Object Detection (Q)
|
91% |
17052
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3155
37.5 IPS |
|
Face Detection (HP)
|
100% |
32957
391.6 IPS |
|
Face Detection (Q)
|
100% |
41661
495.0 IPS |
|
Depth Estimation (SP)
|
100% |
5635
43.4 IPS |
|
Depth Estimation (HP)
|
99% |
84281
649.3 IPS |
|
Depth Estimation (Q)
|
85% |
104196
814.2 IPS |
|
Style Transfer (SP)
|
100% |
18684
24.0 IPS |
|
Style Transfer (HP)
|
100% |
203143
261.1 IPS |
|
Style Transfer (Q)
|
96% |
193167
249.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3945
145.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
38622
1.43 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46832
1.73 KIPS |
|
Text Classification (SP)
|
100% |
2280
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3865
5.16 KIPS |
|
Text Classification (Q)
|
93% |
3841
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
3729
64.2 IPS |
|
Machine Translation (HP)
|
100% |
4311
74.3 IPS |
|
Machine Translation (Q)
|
98% |
4492
77.6 IPS |