User | M91 |
Upload Date | August 15 2025 11:53 AM |
Views | 5 |
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% |
1993
370.6 IPS |
|
Image Classification (HP)
|
100% |
14593
2.71 KIPS |
|
Image Classification (Q)
|
97% |
18286
3.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1768
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
18122
293.8 IPS |
|
Image Segmentation (Q)
|
99% |
23700
384.2 IPS |
|
Pose Estimation (SP)
|
100% |
8716
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
146554
171.0 IPS |
|
Pose Estimation (Q)
|
95% |
288968
338.7 IPS |
|
Object Detection (SP)
|
100% |
2324
184.3 IPS |
|
Object Detection (HP)
|
100% |
15461
1.23 KIPS |
|
Object Detection (Q)
|
91% |
21096
1.69 KIPS |
|
Face Detection (SP)
|
100% |
3617
43.0 IPS |
|
Face Detection (HP)
|
100% |
38993
463.3 IPS |
|
Face Detection (Q)
|
100% |
52753
626.8 IPS |
|
Depth Estimation (SP)
|
100% |
8060
62.1 IPS |
|
Depth Estimation (HP)
|
99% |
93757
722.3 IPS |
|
Depth Estimation (Q)
|
85% |
155499
1.22 KIPS |
|
Style Transfer (SP)
|
100% |
21075
27.1 IPS |
|
Style Transfer (HP)
|
100% |
243549
313.1 IPS |
|
Style Transfer (Q)
|
96% |
294623
380.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5403
199.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
50304
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78146
2.89 KIPS |
|
Text Classification (SP)
|
100% |
3740
4.99 KIPS |
|
Text Classification (HP)
|
99% |
6127
8.18 KIPS |
|
Text Classification (Q)
|
93% |
6108
8.20 KIPS |
|
Machine Translation (SP)
|
100% |
4026
69.3 IPS |
|
Machine Translation (HP)
|
100% |
9029
155.5 IPS |
|
Machine Translation (Q)
|
98% |
10184
176.0 IPS |