User | ElementalOwl |
Upload Date | April 07 2025 03:32 AM |
Views | 2 |
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% |
2030
377.6 IPS |
|
Image Classification (HP)
|
100% |
15774
2.93 KIPS |
|
Image Classification (Q)
|
97% |
23481
4.38 KIPS |
|
Image Segmentation (SP)
|
100% |
1972
32.0 IPS |
|
Image Segmentation (HP)
|
100% |
18363
297.7 IPS |
|
Image Segmentation (Q)
|
99% |
24151
391.5 IPS |
|
Pose Estimation (SP)
|
100% |
8229
9.60 IPS |
|
Pose Estimation (HP)
|
100% |
144355
168.4 IPS |
|
Pose Estimation (Q)
|
95% |
292156
342.4 IPS |
|
Object Detection (SP)
|
100% |
2245
178.1 IPS |
|
Object Detection (HP)
|
100% |
16640
1.32 KIPS |
|
Object Detection (Q)
|
91% |
23222
1.86 KIPS |
|
Face Detection (SP)
|
100% |
3830
45.5 IPS |
|
Face Detection (HP)
|
100% |
41151
489.0 IPS |
|
Face Detection (Q)
|
100% |
61178
726.9 IPS |
|
Depth Estimation (SP)
|
100% |
7910
60.9 IPS |
|
Depth Estimation (HP)
|
99% |
96807
745.8 IPS |
|
Depth Estimation (Q)
|
85% |
165558
1.29 KIPS |
|
Style Transfer (SP)
|
100% |
18784
24.1 IPS |
|
Style Transfer (HP)
|
100% |
247021
317.5 IPS |
|
Style Transfer (Q)
|
96% |
305258
393.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5214
192.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
52610
1.94 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86395
3.19 KIPS |
|
Text Classification (SP)
|
100% |
3457
4.61 KIPS |
|
Text Classification (HP)
|
100% |
5195
6.93 KIPS |
|
Text Classification (Q)
|
93% |
5329
7.15 KIPS |
|
Machine Translation (SP)
|
100% |
4256
73.3 IPS |
|
Machine Translation (HP)
|
100% |
10096
173.9 IPS |
|
Machine Translation (Q)
|
98% |
11517
199.0 IPS |