User | 1145141919810 |
Upload Date | August 26 2025 01:39 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.13 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1599
297.4 IPS |
|
Image Classification (HP)
|
100% |
8764
1.63 KIPS |
|
Image Classification (Q)
|
97% |
10530
1.97 KIPS |
|
Image Segmentation (SP)
|
100% |
942
15.3 IPS |
|
Image Segmentation (HP)
|
100% |
6840
110.9 IPS |
|
Image Segmentation (Q)
|
99% |
13945
226.1 IPS |
|
Pose Estimation (SP)
|
100% |
9763
11.4 IPS |
|
Pose Estimation (HP)
|
100% |
107055
124.9 IPS |
|
Pose Estimation (Q)
|
95% |
187980
220.3 IPS |
|
Object Detection (SP)
|
100% |
1840
146.0 IPS |
|
Object Detection (HP)
|
100% |
11419
905.7 IPS |
|
Object Detection (Q)
|
93% |
14172
1.13 KIPS |
|
Face Detection (SP)
|
100% |
2997
35.6 IPS |
|
Face Detection (HP)
|
100% |
15820
188.0 IPS |
|
Face Detection (Q)
|
100% |
19231
228.5 IPS |
|
Depth Estimation (SP)
|
100% |
5746
44.3 IPS |
|
Depth Estimation (HP)
|
99% |
62646
482.6 IPS |
|
Depth Estimation (Q)
|
85% |
90290
705.9 IPS |
|
Style Transfer (SP)
|
100% |
14896
19.1 IPS |
|
Style Transfer (HP)
|
100% |
159973
205.6 IPS |
|
Style Transfer (Q)
|
96% |
171925
221.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4862
179.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
23065
851.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
33821
1.25 KIPS |
|
Text Classification (SP)
|
100% |
1860
2.48 KIPS |
|
Text Classification (HP)
|
71% |
7142
10.3 KIPS |
|
Text Classification (Q)
|
69% |
6952
10.2 KIPS |
|
Machine Translation (SP)
|
100% |
2239
38.6 IPS |
|
Machine Translation (HP)
|
100% |
3013
51.9 IPS |
|
Machine Translation (Q)
|
98% |
3048
52.7 IPS |