Upload Date | September 02 2025 08:46 AM |
Views | 4 |
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% |
1371
255.0 IPS |
|
Image Classification (HP)
|
100% |
14372
2.67 KIPS |
|
Image Classification (Q)
|
96% |
15690
2.93 KIPS |
|
Image Segmentation (SP)
|
100% |
1467
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
19631
318.2 IPS |
|
Image Segmentation (Q)
|
99% |
24167
391.8 IPS |
|
Pose Estimation (SP)
|
100% |
6847
7.99 IPS |
|
Pose Estimation (HP)
|
100% |
101871
118.9 IPS |
|
Pose Estimation (Q)
|
95% |
106894
125.3 IPS |
|
Object Detection (SP)
|
100% |
1546
122.7 IPS |
|
Object Detection (HP)
|
99% |
15640
1.24 KIPS |
|
Object Detection (Q)
|
91% |
16442
1.31 KIPS |
|
Face Detection (SP)
|
100% |
3113
37.0 IPS |
|
Face Detection (HP)
|
100% |
33952
403.4 IPS |
|
Face Detection (Q)
|
100% |
42881
509.5 IPS |
|
Depth Estimation (SP)
|
100% |
5573
42.9 IPS |
|
Depth Estimation (HP)
|
99% |
84726
652.8 IPS |
|
Depth Estimation (Q)
|
85% |
102479
800.8 IPS |
|
Style Transfer (SP)
|
100% |
18718
24.1 IPS |
|
Style Transfer (HP)
|
100% |
201725
259.3 IPS |
|
Style Transfer (Q)
|
96% |
193186
249.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3939
145.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
38526
1.42 KIPS |
|
Image Super-Resolution (Q)
|
99% |
44600
1.65 KIPS |
|
Text Classification (SP)
|
100% |
2312
3.09 KIPS |
|
Text Classification (HP)
|
99% |
3810
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3807
5.11 KIPS |
|
Machine Translation (SP)
|
100% |
3875
66.7 IPS |
|
Machine Translation (HP)
|
100% |
4242
73.1 IPS |
|
Machine Translation (Q)
|
98% |
4366
75.5 IPS |