| User | dirkjumpertz |
| Upload Date | November 05 2025 02:20 PM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| 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 | 15.36 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2328
433.0 IPS |
|
|
Image Classification (HP)
|
100% |
2203
409.6 IPS |
|
|
Image Classification (Q)
|
96% |
2197
410.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
4008
65.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
4284
69.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
4091
66.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
17003
19.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
18897
22.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
18269
21.4 IPS |
|
|
Object Detection (SP)
|
100% |
2640
209.4 IPS |
|
|
Object Detection (HP)
|
100% |
2675
212.2 IPS |
|
|
Object Detection (Q)
|
92% |
2453
195.8 IPS |
|
|
Face Detection (SP)
|
100% |
6804
80.8 IPS |
|
|
Face Detection (HP)
|
100% |
8553
101.6 IPS |
|
|
Face Detection (Q)
|
100% |
7057
83.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
12372
95.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
13843
106.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
12665
98.9 IPS |
|
|
Style Transfer (SP)
|
100% |
28531
36.7 IPS |
|
|
Style Transfer (HP)
|
100% |
35330
45.4 IPS |
|
|
Style Transfer (Q)
|
96% |
34174
44.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6364
235.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7172
264.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5982
220.9 IPS |
|
|
Text Classification (SP)
|
100% |
2417
3.23 KIPS |
|
|
Text Classification (HP)
|
99% |
4240
5.66 KIPS |
|
|
Text Classification (Q)
|
93% |
4272
5.73 KIPS |
|
|
Machine Translation (SP)
|
100% |
959
16.5 IPS |
|
|
Machine Translation (HP)
|
100% |
1011
17.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1010
17.5 IPS |