User | M91 |
Upload Date | October 14 2025 02:40 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.1 |
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% |
1990
370.1 IPS |
|
Image Classification (HP)
|
100% |
14607
2.72 KIPS |
|
Image Classification (Q)
|
97% |
18642
3.48 KIPS |
|
Image Segmentation (SP)
|
100% |
1779
28.8 IPS |
|
Image Segmentation (HP)
|
100% |
18094
293.3 IPS |
|
Image Segmentation (Q)
|
99% |
23593
382.5 IPS |
|
Pose Estimation (SP)
|
100% |
8553
9.98 IPS |
|
Pose Estimation (HP)
|
100% |
145799
170.1 IPS |
|
Pose Estimation (Q)
|
95% |
284167
333.1 IPS |
|
Object Detection (SP)
|
100% |
2267
179.8 IPS |
|
Object Detection (HP)
|
100% |
15519
1.23 KIPS |
|
Object Detection (Q)
|
91% |
21233
1.70 KIPS |
|
Face Detection (SP)
|
100% |
3537
42.0 IPS |
|
Face Detection (HP)
|
100% |
40017
475.5 IPS |
|
Face Detection (Q)
|
100% |
53101
631.0 IPS |
|
Depth Estimation (SP)
|
100% |
7821
60.3 IPS |
|
Depth Estimation (HP)
|
99% |
93684
721.8 IPS |
|
Depth Estimation (Q)
|
85% |
153721
1.20 KIPS |
|
Style Transfer (SP)
|
100% |
20617
26.5 IPS |
|
Style Transfer (HP)
|
100% |
244159
313.9 IPS |
|
Style Transfer (Q)
|
96% |
293905
379.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5221
192.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
50712
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79854
2.95 KIPS |
|
Text Classification (SP)
|
100% |
3687
4.92 KIPS |
|
Text Classification (HP)
|
99% |
6139
8.19 KIPS |
|
Text Classification (Q)
|
93% |
6152
8.26 KIPS |
|
Machine Translation (SP)
|
100% |
3960
68.2 IPS |
|
Machine Translation (HP)
|
100% |
9184
158.2 IPS |
|
Machine Translation (Q)
|
98% |
10300
178.0 IPS |