Upload Date | August 06 2025 05:55 PM |
Views | 5 |
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% |
2067
384.5 IPS |
|
Image Classification (HP)
|
100% |
15403
2.86 KIPS |
|
Image Classification (Q)
|
97% |
20862
3.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1975
32.0 IPS |
|
Image Segmentation (HP)
|
100% |
18249
295.8 IPS |
|
Image Segmentation (Q)
|
99% |
24201
392.3 IPS |
|
Pose Estimation (SP)
|
100% |
9532
11.1 IPS |
|
Pose Estimation (HP)
|
100% |
153321
178.9 IPS |
|
Pose Estimation (Q)
|
95% |
292153
342.4 IPS |
|
Object Detection (SP)
|
100% |
2374
188.3 IPS |
|
Object Detection (HP)
|
100% |
16257
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22298
1.78 KIPS |
|
Face Detection (SP)
|
100% |
3919
46.6 IPS |
|
Face Detection (HP)
|
100% |
39699
471.7 IPS |
|
Face Detection (Q)
|
100% |
56757
674.4 IPS |
|
Depth Estimation (SP)
|
100% |
8301
64.0 IPS |
|
Depth Estimation (HP)
|
99% |
95075
732.5 IPS |
|
Depth Estimation (Q)
|
85% |
159426
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20847
26.8 IPS |
|
Style Transfer (HP)
|
100% |
245224
315.2 IPS |
|
Style Transfer (Q)
|
96% |
303059
391.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5649
208.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
51833
1.91 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86124
3.18 KIPS |
|
Text Classification (SP)
|
100% |
3384
4.52 KIPS |
|
Text Classification (HP)
|
100% |
4864
6.49 KIPS |
|
Text Classification (Q)
|
93% |
5105
6.85 KIPS |
|
Machine Translation (SP)
|
100% |
4232
72.9 IPS |
|
Machine Translation (HP)
|
100% |
10137
174.6 IPS |
|
Machine Translation (Q)
|
98% |
11671
201.7 IPS |