User | xiayang |
Upload Date | June 09 2025 12:40 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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 | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2064
383.9 IPS |
|
Image Classification (HP)
|
100% |
15276
2.84 KIPS |
|
Image Classification (Q)
|
97% |
19438
3.63 KIPS |
|
Image Segmentation (SP)
|
100% |
1958
31.7 IPS |
|
Image Segmentation (HP)
|
100% |
18312
296.8 IPS |
|
Image Segmentation (Q)
|
99% |
24207
392.4 IPS |
|
Pose Estimation (SP)
|
100% |
9568
11.2 IPS |
|
Pose Estimation (HP)
|
100% |
153425
179.0 IPS |
|
Pose Estimation (Q)
|
95% |
292496
342.8 IPS |
|
Object Detection (SP)
|
100% |
2370
188.0 IPS |
|
Object Detection (HP)
|
100% |
16289
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22454
1.79 KIPS |
|
Face Detection (SP)
|
100% |
3928
46.7 IPS |
|
Face Detection (HP)
|
100% |
41245
490.1 IPS |
|
Face Detection (Q)
|
100% |
58158
691.0 IPS |
|
Depth Estimation (SP)
|
100% |
8340
64.3 IPS |
|
Depth Estimation (HP)
|
99% |
95351
734.6 IPS |
|
Depth Estimation (Q)
|
85% |
159184
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
20833
26.8 IPS |
|
Style Transfer (HP)
|
100% |
246163
316.4 IPS |
|
Style Transfer (Q)
|
96% |
303718
391.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5414
199.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50635
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87679
3.24 KIPS |
|
Text Classification (SP)
|
100% |
3391
4.53 KIPS |
|
Text Classification (HP)
|
100% |
4374
5.84 KIPS |
|
Text Classification (Q)
|
93% |
4341
5.83 KIPS |
|
Machine Translation (SP)
|
100% |
4164
71.7 IPS |
|
Machine Translation (HP)
|
100% |
10136
174.6 IPS |
|
Machine Translation (Q)
|
98% |
11493
198.6 IPS |