User | M91 |
Upload Date | April 03 2025 11:39 AM |
Views | 3 |
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% |
1335
248.4 IPS |
|
Image Classification (HP)
|
100% |
11829
2.20 KIPS |
|
Image Classification (Q)
|
97% |
15016
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1262
20.5 IPS |
|
Image Segmentation (HP)
|
100% |
13415
217.5 IPS |
|
Image Segmentation (Q)
|
99% |
18770
304.3 IPS |
|
Pose Estimation (SP)
|
100% |
4843
5.65 IPS |
|
Pose Estimation (HP)
|
100% |
97154
113.4 IPS |
|
Pose Estimation (Q)
|
95% |
171990
201.6 IPS |
|
Object Detection (SP)
|
100% |
1681
133.3 IPS |
|
Object Detection (HP)
|
100% |
13216
1.05 KIPS |
|
Object Detection (Q)
|
91% |
16002
1.28 KIPS |
|
Face Detection (SP)
|
100% |
2806
33.3 IPS |
|
Face Detection (HP)
|
100% |
28394
337.4 IPS |
|
Face Detection (Q)
|
100% |
40785
484.6 IPS |
|
Depth Estimation (SP)
|
100% |
5646
43.5 IPS |
|
Depth Estimation (HP)
|
99% |
69285
533.8 IPS |
|
Depth Estimation (Q)
|
85% |
114489
895.1 IPS |
|
Style Transfer (SP)
|
100% |
12506
16.1 IPS |
|
Style Transfer (HP)
|
100% |
163167
209.8 IPS |
|
Style Transfer (Q)
|
96% |
224654
289.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4401
162.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
37116
1.37 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59603
2.20 KIPS |
|
Text Classification (SP)
|
100% |
2615
3.49 KIPS |
|
Text Classification (HP)
|
100% |
3876
5.17 KIPS |
|
Text Classification (Q)
|
93% |
3834
5.15 KIPS |
|
Machine Translation (SP)
|
100% |
3323
57.2 IPS |
|
Machine Translation (HP)
|
100% |
8448
145.5 IPS |
|
Machine Translation (Q)
|
98% |
9190
158.8 IPS |