Upload Date | June 12 2025 11:19 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1380
256.6 IPS |
|
Image Classification (HP)
|
100% |
13893
2.58 KIPS |
|
Image Classification (Q)
|
96% |
15730
2.94 KIPS |
|
Image Segmentation (SP)
|
100% |
1520
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
19607
317.8 IPS |
|
Image Segmentation (Q)
|
99% |
24285
393.7 IPS |
|
Pose Estimation (SP)
|
100% |
6839
7.98 IPS |
|
Pose Estimation (HP)
|
100% |
104600
122.1 IPS |
|
Pose Estimation (Q)
|
95% |
105263
123.4 IPS |
|
Object Detection (SP)
|
100% |
1536
121.9 IPS |
|
Object Detection (HP)
|
99% |
15789
1.26 KIPS |
|
Object Detection (Q)
|
91% |
18368
1.47 KIPS |
|
Face Detection (SP)
|
100% |
3082
36.6 IPS |
|
Face Detection (HP)
|
100% |
33391
396.8 IPS |
|
Face Detection (Q)
|
100% |
42559
505.7 IPS |
|
Depth Estimation (SP)
|
100% |
5617
43.3 IPS |
|
Depth Estimation (HP)
|
99% |
87005
670.3 IPS |
|
Depth Estimation (Q)
|
85% |
105634
825.5 IPS |
|
Style Transfer (SP)
|
100% |
18719
24.1 IPS |
|
Style Transfer (HP)
|
100% |
202275
260.0 IPS |
|
Style Transfer (Q)
|
96% |
195725
252.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4067
150.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
39810
1.47 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47697
1.76 KIPS |
|
Text Classification (SP)
|
100% |
2320
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3953
5.28 KIPS |
|
Text Classification (Q)
|
93% |
3924
5.27 KIPS |
|
Machine Translation (SP)
|
100% |
3684
63.5 IPS |
|
Machine Translation (HP)
|
100% |
4301
74.1 IPS |
|
Machine Translation (Q)
|
98% |
4454
77.0 IPS |