Upload Date | September 13 2025 01:31 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 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% |
2016
374.8 IPS |
|
Image Classification (HP)
|
100% |
14696
2.73 KIPS |
|
Image Classification (Q)
|
97% |
19214
3.59 KIPS |
|
Image Segmentation (SP)
|
100% |
1752
28.4 IPS |
|
Image Segmentation (HP)
|
100% |
18118
293.7 IPS |
|
Image Segmentation (Q)
|
99% |
23491
380.8 IPS |
|
Pose Estimation (SP)
|
100% |
8107
9.46 IPS |
|
Pose Estimation (HP)
|
100% |
144399
168.5 IPS |
|
Pose Estimation (Q)
|
95% |
281780
330.3 IPS |
|
Object Detection (SP)
|
100% |
2276
180.5 IPS |
|
Object Detection (HP)
|
100% |
15522
1.23 KIPS |
|
Object Detection (Q)
|
91% |
21677
1.73 KIPS |
|
Face Detection (SP)
|
100% |
3591
42.7 IPS |
|
Face Detection (HP)
|
100% |
39544
469.9 IPS |
|
Face Detection (Q)
|
100% |
52898
628.5 IPS |
|
Depth Estimation (SP)
|
100% |
7931
61.1 IPS |
|
Depth Estimation (HP)
|
99% |
94075
724.8 IPS |
|
Depth Estimation (Q)
|
85% |
150416
1.18 KIPS |
|
Style Transfer (SP)
|
100% |
21216
27.3 IPS |
|
Style Transfer (HP)
|
100% |
243581
313.1 IPS |
|
Style Transfer (Q)
|
96% |
294521
380.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5147
190.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
52504
1.94 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78634
2.90 KIPS |
|
Text Classification (SP)
|
100% |
3682
4.91 KIPS |
|
Text Classification (HP)
|
99% |
6109
8.15 KIPS |
|
Text Classification (Q)
|
93% |
6248
8.39 KIPS |
|
Machine Translation (SP)
|
100% |
4020
69.2 IPS |
|
Machine Translation (HP)
|
100% |
9020
155.4 IPS |
|
Machine Translation (Q)
|
98% |
10081
174.2 IPS |