| Upload Date | February 07 2026 04:05 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 26.2.1 |
| Model | iPad Pro 11-inch (M4) |
| Model ID | iPad16,3 |
| Motherboard | J717AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.29 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2123
394.8 IPS |
|
|
Image Classification (HP)
|
100% |
17011
3.16 KIPS |
|
|
Image Classification (Q)
|
97% |
22968
4.29 KIPS |
|
|
Image Segmentation (SP)
|
100% |
2166
35.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
22374
362.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
30819
499.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
10050
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
122782
143.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
232433
272.4 IPS |
|
|
Object Detection (SP)
|
100% |
2459
195.0 IPS |
|
|
Object Detection (HP)
|
100% |
17815
1.41 KIPS |
|
|
Object Detection (Q)
|
91% |
25831
2.06 KIPS |
|
|
Face Detection (SP)
|
100% |
4354
51.7 IPS |
|
|
Face Detection (HP)
|
100% |
42764
508.1 IPS |
|
|
Face Detection (Q)
|
100% |
62578
743.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
8605
66.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
98682
760.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
163856
1.28 KIPS |
|
|
Style Transfer (SP)
|
100% |
24505
31.5 IPS |
|
|
Style Transfer (HP)
|
100% |
232274
298.6 IPS |
|
|
Style Transfer (Q)
|
96% |
319985
412.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6080
224.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50488
1.86 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
83327
3.08 KIPS |
|
|
Text Classification (SP)
|
100% |
3349
4.47 KIPS |
|
|
Text Classification (HP)
|
99% |
5858
7.82 KIPS |
|
|
Text Classification (Q)
|
93% |
5726
7.68 KIPS |
|
|
Machine Translation (SP)
|
100% |
4589
79.0 IPS |
|
|
Machine Translation (HP)
|
100% |
16518
284.5 IPS |
|
|
Machine Translation (Q)
|
98% |
18132
313.3 IPS |