User | M91 |
Upload Date | July 21 2025 08:22 PM |
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% |
2004
372.6 IPS |
|
Image Classification (HP)
|
100% |
14488
2.69 KIPS |
|
Image Classification (Q)
|
97% |
18690
3.49 KIPS |
|
Image Segmentation (SP)
|
100% |
1783
28.9 IPS |
|
Image Segmentation (HP)
|
100% |
18156
294.3 IPS |
|
Image Segmentation (Q)
|
99% |
23397
379.3 IPS |
|
Pose Estimation (SP)
|
100% |
8482
9.90 IPS |
|
Pose Estimation (HP)
|
100% |
143647
167.6 IPS |
|
Pose Estimation (Q)
|
95% |
286951
336.3 IPS |
|
Object Detection (SP)
|
100% |
2296
182.1 IPS |
|
Object Detection (HP)
|
100% |
15972
1.27 KIPS |
|
Object Detection (Q)
|
91% |
21294
1.70 KIPS |
|
Face Detection (SP)
|
100% |
3506
41.7 IPS |
|
Face Detection (HP)
|
100% |
39094
464.5 IPS |
|
Face Detection (Q)
|
100% |
52301
621.5 IPS |
|
Depth Estimation (SP)
|
100% |
7796
60.1 IPS |
|
Depth Estimation (HP)
|
99% |
93870
723.2 IPS |
|
Depth Estimation (Q)
|
85% |
148599
1.16 KIPS |
|
Style Transfer (SP)
|
100% |
20444
26.3 IPS |
|
Style Transfer (HP)
|
100% |
243921
313.6 IPS |
|
Style Transfer (Q)
|
96% |
295652
381.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5122
189.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
50602
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77843
2.87 KIPS |
|
Text Classification (SP)
|
100% |
3631
4.85 KIPS |
|
Text Classification (HP)
|
99% |
6100
8.14 KIPS |
|
Text Classification (Q)
|
93% |
5964
8.00 KIPS |
|
Machine Translation (SP)
|
100% |
4031
69.4 IPS |
|
Machine Translation (HP)
|
100% |
11032
190.0 IPS |
|
Machine Translation (Q)
|
98% |
12714
219.7 IPS |