| Upload Date | January 05 2026 11:36 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.2 |
| Model | iPhone 16 Pro Max |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | Apple A18 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1983
368.8 IPS |
|
|
Image Classification (HP)
|
100% |
3469
645.0 IPS |
|
|
Image Classification (Q)
|
96% |
2319
433.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1861
30.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2879
46.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
3313
53.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
9356
10.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
18591
21.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
15875
18.6 IPS |
|
|
Object Detection (SP)
|
100% |
2354
186.7 IPS |
|
|
Object Detection (HP)
|
97% |
3742
297.9 IPS |
|
|
Object Detection (Q)
|
94% |
2648
211.1 IPS |
|
|
Face Detection (SP)
|
100% |
3648
43.3 IPS |
|
|
Face Detection (HP)
|
100% |
6956
82.6 IPS |
|
|
Face Detection (Q)
|
100% |
4034
47.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
8245
63.5 IPS |
|
|
Depth Estimation (HP)
|
97% |
13799
106.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
9776
76.3 IPS |
|
|
Style Transfer (SP)
|
100% |
22548
29.0 IPS |
|
|
Style Transfer (HP)
|
100% |
38206
49.1 IPS |
|
|
Style Transfer (Q)
|
96% |
31450
40.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5645
208.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7332
270.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5175
191.1 IPS |
|
|
Text Classification (SP)
|
100% |
3755
5.01 KIPS |
|
|
Text Classification (HP)
|
99% |
6288
8.39 KIPS |
|
|
Text Classification (Q)
|
93% |
6274
8.42 KIPS |
|
|
Machine Translation (SP)
|
100% |
4096
70.6 IPS |
|
|
Machine Translation (HP)
|
98% |
7308
126.3 IPS |
|
|
Machine Translation (Q)
|
98% |
7341
126.9 IPS |