User | rafaexnexus |
Upload Date | October 04 2025 03:20 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 26.0.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1551
288.5 IPS |
|
Image Classification (HP)
|
100% |
10408
1.94 KIPS |
|
Image Classification (Q)
|
97% |
15401
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1534
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
16526
267.9 IPS |
|
Image Segmentation (Q)
|
99% |
21074
341.6 IPS |
|
Pose Estimation (SP)
|
100% |
7499
8.75 IPS |
|
Pose Estimation (HP)
|
100% |
105555
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
201535
236.2 IPS |
|
Object Detection (SP)
|
100% |
1665
132.0 IPS |
|
Object Detection (HP)
|
100% |
13281
1.05 KIPS |
|
Object Detection (Q)
|
91% |
17439
1.39 KIPS |
|
Face Detection (SP)
|
100% |
3063
36.4 IPS |
|
Face Detection (HP)
|
100% |
33738
400.9 IPS |
|
Face Detection (Q)
|
100% |
50150
595.9 IPS |
|
Depth Estimation (SP)
|
100% |
6886
53.1 IPS |
|
Depth Estimation (HP)
|
99% |
78087
601.6 IPS |
|
Depth Estimation (Q)
|
85% |
125758
983.2 IPS |
|
Style Transfer (SP)
|
100% |
20872
26.8 IPS |
|
Style Transfer (HP)
|
100% |
201975
259.6 IPS |
|
Style Transfer (Q)
|
96% |
249396
321.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4666
172.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34166
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55363
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3248
4.33 KIPS |
|
Text Classification (HP)
|
99% |
5500
7.34 KIPS |
|
Text Classification (Q)
|
93% |
5495
7.37 KIPS |
|
Machine Translation (SP)
|
100% |
3075
53.0 IPS |
|
Machine Translation (HP)
|
100% |
6068
104.5 IPS |
|
Machine Translation (Q)
|
98% |
6918
119.6 IPS |