User | Yearcakes |
Upload Date | September 20 2025 04:54 AM |
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 |
Model ID | iPhone17,1 |
Motherboard | D93AP |
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 | 7.46 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2059
382.8 IPS |
|
Image Classification (HP)
|
100% |
14246
2.65 KIPS |
|
Image Classification (Q)
|
97% |
17931
3.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1848
30.0 IPS |
|
Image Segmentation (HP)
|
100% |
17962
291.2 IPS |
|
Image Segmentation (Q)
|
99% |
23683
383.9 IPS |
|
Pose Estimation (SP)
|
100% |
9787
11.4 IPS |
|
Pose Estimation (HP)
|
100% |
153047
178.6 IPS |
|
Pose Estimation (Q)
|
95% |
293742
344.3 IPS |
|
Object Detection (SP)
|
100% |
2406
190.8 IPS |
|
Object Detection (HP)
|
100% |
16019
1.27 KIPS |
|
Object Detection (Q)
|
91% |
21104
1.69 KIPS |
|
Face Detection (SP)
|
100% |
3832
45.5 IPS |
|
Face Detection (HP)
|
100% |
40106
476.5 IPS |
|
Face Detection (Q)
|
100% |
52820
627.6 IPS |
|
Depth Estimation (SP)
|
100% |
8424
64.9 IPS |
|
Depth Estimation (HP)
|
99% |
94430
727.5 IPS |
|
Depth Estimation (Q)
|
85% |
154786
1.21 KIPS |
|
Style Transfer (SP)
|
100% |
24563
31.6 IPS |
|
Style Transfer (HP)
|
100% |
245775
315.9 IPS |
|
Style Transfer (Q)
|
96% |
296328
382.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5886
217.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
51486
1.90 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82799
3.06 KIPS |
|
Text Classification (SP)
|
100% |
3710
4.95 KIPS |
|
Text Classification (HP)
|
99% |
6153
8.21 KIPS |
|
Text Classification (Q)
|
93% |
6084
8.17 KIPS |
|
Machine Translation (SP)
|
100% |
4278
73.7 IPS |
|
Machine Translation (HP)
|
100% |
9636
166.0 IPS |
|
Machine Translation (Q)
|
98% |
10209
176.4 IPS |