Upload Date | September 22 2025 01:13 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
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% |
2022
376.0 IPS |
|
Image Classification (HP)
|
100% |
14743
2.74 KIPS |
|
Image Classification (Q)
|
97% |
19325
3.61 KIPS |
|
Image Segmentation (SP)
|
100% |
1779
28.8 IPS |
|
Image Segmentation (HP)
|
100% |
18152
294.3 IPS |
|
Image Segmentation (Q)
|
99% |
23684
383.9 IPS |
|
Pose Estimation (SP)
|
100% |
8917
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
147624
172.3 IPS |
|
Pose Estimation (Q)
|
95% |
288063
337.6 IPS |
|
Object Detection (SP)
|
100% |
2293
181.9 IPS |
|
Object Detection (HP)
|
100% |
15673
1.24 KIPS |
|
Object Detection (Q)
|
91% |
21352
1.71 KIPS |
|
Face Detection (SP)
|
100% |
3501
41.6 IPS |
|
Face Detection (HP)
|
100% |
39419
468.4 IPS |
|
Face Detection (Q)
|
100% |
53112
631.1 IPS |
|
Depth Estimation (SP)
|
100% |
7983
61.5 IPS |
|
Depth Estimation (HP)
|
99% |
94119
725.1 IPS |
|
Depth Estimation (Q)
|
85% |
158323
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
21417
27.5 IPS |
|
Style Transfer (HP)
|
100% |
244442
314.2 IPS |
|
Style Transfer (Q)
|
96% |
293797
379.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5331
196.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
51370
1.90 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79451
2.93 KIPS |
|
Text Classification (SP)
|
100% |
3679
4.91 KIPS |
|
Text Classification (HP)
|
99% |
6124
8.17 KIPS |
|
Text Classification (Q)
|
93% |
6119
8.21 KIPS |
|
Machine Translation (SP)
|
100% |
4013
69.1 IPS |
|
Machine Translation (HP)
|
100% |
9064
156.1 IPS |
|
Machine Translation (Q)
|
98% |
10263
177.4 IPS |