| User | FangYuan |
| Upload Date | November 21 2026 08:38 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 27.3 |
| Model | iPhone 12 Pro Max |
| Model ID | iPhone13,4 |
| Motherboard | D54pAP |
| 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 | 5.56 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1214
225.8 IPS |
|
|
Image Classification (HP)
|
100% |
4471
831.4 IPS |
|
|
Image Classification (Q)
|
97% |
4759
888.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
1112
18.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
8347
135.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
9030
146.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
4270
4.98 IPS |
|
|
Pose Estimation (HP)
|
100% |
61222
71.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
61442
72.0 IPS |
|
|
Object Detection (SP)
|
100% |
1224
97.1 IPS |
|
|
Object Detection (HP)
|
99% |
5867
466.7 IPS |
|
|
Object Detection (Q)
|
89% |
5422
434.0 IPS |
|
|
Face Detection (SP)
|
100% |
2501
29.7 IPS |
|
|
Face Detection (HP)
|
100% |
15110
179.5 IPS |
|
|
Face Detection (Q)
|
100% |
12357
146.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
4464
34.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
39153
301.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
37399
292.6 IPS |
|
|
Style Transfer (SP)
|
100% |
12187
15.7 IPS |
|
|
Style Transfer (HP)
|
100% |
117169
150.6 IPS |
|
|
Style Transfer (Q)
|
96% |
110492
142.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2373
87.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
19007
701.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
19561
722.3 IPS |
|
|
Text Classification (SP)
|
100% |
4057
5.41 KIPS |
|
|
Text Classification (HP)
|
100% |
1907
2.54 KIPS |
|
|
Text Classification (Q)
|
93% |
1924
2.58 KIPS |
|
|
Machine Translation (SP)
|
100% |
2230
38.4 IPS |
|
|
Machine Translation (HP)
|
100% |
4734
81.6 IPS |
|
|
Machine Translation (Q)
|
98% |
5285
91.3 IPS |