| User | tokris |
| Upload Date | May 20 2026 07:12 PM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 26.5 |
| 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% |
1306
242.8 IPS |
|
|
Image Classification (HP)
|
100% |
6240
1.16 KIPS |
|
|
Image Classification (Q)
|
97% |
5972
1.11 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1342
21.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
9112
147.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
9531
154.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
5876
6.86 IPS |
|
|
Pose Estimation (HP)
|
100% |
68191
79.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
65047
76.2 IPS |
|
|
Object Detection (SP)
|
100% |
1391
110.3 IPS |
|
|
Object Detection (HP)
|
99% |
7437
591.6 IPS |
|
|
Object Detection (Q)
|
89% |
6895
552.0 IPS |
|
|
Face Detection (SP)
|
100% |
2932
34.8 IPS |
|
|
Face Detection (HP)
|
100% |
14898
177.0 IPS |
|
|
Face Detection (Q)
|
100% |
13908
165.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
5404
41.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
46225
356.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
48111
376.4 IPS |
|
|
Style Transfer (SP)
|
100% |
16193
20.8 IPS |
|
|
Style Transfer (HP)
|
100% |
122225
157.1 IPS |
|
|
Style Transfer (Q)
|
96% |
114688
148.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3440
127.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
23974
885.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
24445
902.6 IPS |
|
|
Text Classification (SP)
|
99% |
4494
6.00 KIPS |
|
|
Text Classification (HP)
|
99% |
7149
9.54 KIPS |
|
|
Text Classification (Q)
|
93% |
7060
9.47 KIPS |
|
|
Machine Translation (SP)
|
100% |
2488
42.9 IPS |
|
|
Machine Translation (HP)
|
100% |
2802
48.3 IPS |
|
|
Machine Translation (Q)
|
98% |
2881
49.8 IPS |