| Upload Date | November 22 2026 02:53 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 27.2.1 |
| 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% |
1314
244.5 IPS |
|
|
Image Classification (HP)
|
100% |
9627
1.79 KIPS |
|
|
Image Classification (Q)
|
97% |
11096
2.07 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1459
23.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
18445
299.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
22589
366.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
5430
6.34 IPS |
|
|
Pose Estimation (HP)
|
100% |
102193
119.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
103888
121.8 IPS |
|
|
Object Detection (SP)
|
100% |
1457
115.5 IPS |
|
|
Object Detection (HP)
|
99% |
12079
960.9 IPS |
|
|
Object Detection (Q)
|
89% |
13500
1.08 KIPS |
|
|
Face Detection (SP)
|
100% |
3126
37.1 IPS |
|
|
Face Detection (HP)
|
100% |
31844
378.4 IPS |
|
|
Face Detection (Q)
|
100% |
42175
501.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
5229
40.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
76262
587.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
94721
741.0 IPS |
|
|
Style Transfer (SP)
|
100% |
16831
21.6 IPS |
|
|
Style Transfer (HP)
|
100% |
209377
269.2 IPS |
|
|
Style Transfer (Q)
|
96% |
197461
254.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3225
119.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
31687
1.17 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
35006
1.29 KIPS |
|
|
Text Classification (SP)
|
100% |
4337
5.79 KIPS |
|
|
Text Classification (HP)
|
99% |
6743
9.00 KIPS |
|
|
Text Classification (Q)
|
93% |
6685
8.97 KIPS |
|
|
Machine Translation (SP)
|
100% |
3605
62.1 IPS |
|
|
Machine Translation (HP)
|
100% |
3796
65.4 IPS |
|
|
Machine Translation (Q)
|
98% |
3858
66.7 IPS |