| Upload Date | February 07 2026 04:06 PM |
| Views | 1 |
| 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% |
2111
392.6 IPS |
|
|
Image Classification (HP)
|
100% |
17055
3.17 KIPS |
|
|
Image Classification (Q)
|
97% |
23027
4.30 KIPS |
|
|
Image Segmentation (SP)
|
100% |
2143
34.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
22380
362.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
30803
499.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
10057
11.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
122748
143.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
233205
273.3 IPS |
|
|
Object Detection (SP)
|
100% |
2458
195.0 IPS |
|
|
Object Detection (HP)
|
100% |
17760
1.41 KIPS |
|
|
Object Detection (Q)
|
91% |
25928
2.07 KIPS |
|
|
Face Detection (SP)
|
100% |
4332
51.5 IPS |
|
|
Face Detection (HP)
|
100% |
42670
507.0 IPS |
|
|
Face Detection (Q)
|
100% |
62559
743.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
8610
66.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
98801
761.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
166590
1.30 KIPS |
|
|
Style Transfer (SP)
|
100% |
24516
31.5 IPS |
|
|
Style Transfer (HP)
|
100% |
232587
299.0 IPS |
|
|
Style Transfer (Q)
|
96% |
319033
411.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6086
224.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50374
1.86 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
82012
3.03 KIPS |
|
|
Text Classification (SP)
|
100% |
3260
4.35 KIPS |
|
|
Text Classification (HP)
|
99% |
5714
7.63 KIPS |
|
|
Text Classification (Q)
|
93% |
5761
7.73 KIPS |
|
|
Machine Translation (SP)
|
100% |
4552
78.4 IPS |
|
|
Machine Translation (HP)
|
100% |
16579
285.6 IPS |
|
|
Machine Translation (Q)
|
98% |
18170
314.0 IPS |