| Upload Date | December 13 2025 03:04 PM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.7.3 |
| Model | iPad Pro (11-inch 3rd generation) |
| Model ID | iPad13,5 |
| Motherboard | J517xAP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 15.37 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1413
262.7 IPS |
|
|
Image Classification (HP)
|
100% |
6187
1.15 KIPS |
|
|
Image Classification (Q)
|
96% |
5880
1.10 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1357
22.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
9692
157.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
9946
161.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
6492
7.57 IPS |
|
|
Pose Estimation (HP)
|
100% |
66758
77.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
66689
78.2 IPS |
|
|
Object Detection (SP)
|
100% |
1508
119.6 IPS |
|
|
Object Detection (HP)
|
99% |
7256
577.2 IPS |
|
|
Object Detection (Q)
|
91% |
6903
551.6 IPS |
|
|
Face Detection (SP)
|
100% |
3017
35.9 IPS |
|
|
Face Detection (HP)
|
100% |
16363
194.4 IPS |
|
|
Face Detection (Q)
|
100% |
15219
180.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
5651
43.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
47256
364.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
47853
373.9 IPS |
|
|
Style Transfer (SP)
|
100% |
16964
21.8 IPS |
|
|
Style Transfer (HP)
|
100% |
120125
154.4 IPS |
|
|
Style Transfer (Q)
|
96% |
112757
145.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3680
135.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
23056
851.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
23813
879.3 IPS |
|
|
Text Classification (SP)
|
100% |
2292
3.06 KIPS |
|
|
Text Classification (HP)
|
100% |
3922
5.23 KIPS |
|
|
Text Classification (Q)
|
93% |
3892
5.22 KIPS |
|
|
Machine Translation (SP)
|
100% |
2478
42.7 IPS |
|
|
Machine Translation (HP)
|
100% |
3526
60.7 IPS |
|
|
Machine Translation (Q)
|
98% |
3660
63.3 IPS |