Upload Date | September 04 2025 01:15 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
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 | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2074
385.6 IPS |
|
Image Classification (HP)
|
100% |
15475
2.88 KIPS |
|
Image Classification (Q)
|
97% |
20806
3.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1968
31.9 IPS |
|
Image Segmentation (HP)
|
100% |
18275
296.2 IPS |
|
Image Segmentation (Q)
|
99% |
24136
391.3 IPS |
|
Pose Estimation (SP)
|
100% |
8557
9.98 IPS |
|
Pose Estimation (HP)
|
100% |
148744
173.6 IPS |
|
Pose Estimation (Q)
|
95% |
291002
341.1 IPS |
|
Object Detection (SP)
|
100% |
2297
182.2 IPS |
|
Object Detection (HP)
|
100% |
16262
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22720
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3747
44.5 IPS |
|
Face Detection (HP)
|
100% |
41146
488.9 IPS |
|
Face Detection (Q)
|
100% |
57748
686.2 IPS |
|
Depth Estimation (SP)
|
100% |
7952
61.3 IPS |
|
Depth Estimation (HP)
|
99% |
94752
730.0 IPS |
|
Depth Estimation (Q)
|
85% |
164229
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
18911
24.3 IPS |
|
Style Transfer (HP)
|
100% |
245827
316.0 IPS |
|
Style Transfer (Q)
|
96% |
306343
395.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5142
189.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50266
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86067
3.18 KIPS |
|
Text Classification (SP)
|
100% |
3429
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4772
6.37 KIPS |
|
Text Classification (Q)
|
93% |
4876
6.54 KIPS |
|
Machine Translation (SP)
|
100% |
4159
71.6 IPS |
|
Machine Translation (HP)
|
100% |
10279
177.1 IPS |
|
Machine Translation (Q)
|
98% |
11562
199.8 IPS |