| User | tokris |
| Upload Date | January 13 2026 01:16 PM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,11 |
| Motherboard | J523xAP |
| 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 | 15.34 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1935
359.8 IPS |
|
|
Image Classification (HP)
|
100% |
2050
381.2 IPS |
|
|
Image Classification (Q)
|
94% |
1842
344.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
3995
64.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
4251
68.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
4081
66.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
16829
19.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
18848
22.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
18306
21.4 IPS |
|
|
Object Detection (SP)
|
100% |
2678
212.4 IPS |
|
|
Object Detection (HP)
|
100% |
2718
215.6 IPS |
|
|
Object Detection (Q)
|
90% |
2419
193.4 IPS |
|
|
Face Detection (SP)
|
100% |
7048
83.8 IPS |
|
|
Face Detection (HP)
|
100% |
8896
105.7 IPS |
|
|
Face Detection (Q)
|
100% |
7120
84.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
12387
95.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
13807
106.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
12583
98.4 IPS |
|
|
Style Transfer (SP)
|
100% |
28527
36.7 IPS |
|
|
Style Transfer (HP)
|
100% |
35248
45.3 IPS |
|
|
Style Transfer (Q)
|
96% |
34163
44.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6136
226.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6812
251.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5819
214.9 IPS |
|
|
Text Classification (SP)
|
100% |
2336
3.12 KIPS |
|
|
Text Classification (HP)
|
99% |
3995
5.33 KIPS |
|
|
Text Classification (Q)
|
93% |
3963
5.32 KIPS |
|
|
Machine Translation (SP)
|
100% |
964
16.6 IPS |
|
|
Machine Translation (HP)
|
100% |
1006
17.3 IPS |
|
|
Machine Translation (Q)
|
98% |
1002
17.3 IPS |