| Upload Date | December 01 2025 09:02 PM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.7.2 |
| Model | iPhone 12 Pro |
| Model ID | iPhone13,3 |
| Motherboard | D53pAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.58 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1275
237.0 IPS |
|
|
Image Classification (HP)
|
100% |
1933
359.5 IPS |
|
|
Image Classification (Q)
|
96% |
1369
255.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1036
16.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
1731
28.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
2167
35.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
3886
4.53 IPS |
|
|
Pose Estimation (HP)
|
100% |
8411
9.81 IPS |
|
|
Pose Estimation (Q)
|
95% |
7413
8.69 IPS |
|
|
Object Detection (SP)
|
100% |
1086
86.1 IPS |
|
|
Object Detection (HP)
|
97% |
2161
172.1 IPS |
|
|
Object Detection (Q)
|
94% |
1545
123.1 IPS |
|
|
Face Detection (SP)
|
100% |
2158
25.6 IPS |
|
|
Face Detection (HP)
|
100% |
4627
55.0 IPS |
|
|
Face Detection (Q)
|
100% |
2480
29.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
3394
26.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
7503
58.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
5428
42.4 IPS |
|
|
Style Transfer (SP)
|
100% |
9646
12.4 IPS |
|
|
Style Transfer (HP)
|
100% |
17701
22.8 IPS |
|
|
Style Transfer (Q)
|
96% |
15238
19.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2233
82.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3594
132.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2686
99.2 IPS |
|
|
Text Classification (SP)
|
100% |
2133
2.85 KIPS |
|
|
Text Classification (HP)
|
100% |
3626
4.84 KIPS |
|
|
Text Classification (Q)
|
93% |
3644
4.89 KIPS |
|
|
Machine Translation (SP)
|
100% |
1759
30.3 IPS |
|
|
Machine Translation (HP)
|
98% |
3662
63.3 IPS |
|
|
Machine Translation (Q)
|
98% |
3546
61.3 IPS |