User | M91 |
Upload Date | April 07 2025 08:42 PM |
Views | 2 |
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% |
2079
386.6 IPS |
|
Image Classification (HP)
|
100% |
15347
2.85 KIPS |
|
Image Classification (Q)
|
97% |
19791
3.69 KIPS |
|
Image Segmentation (SP)
|
100% |
1989
32.2 IPS |
|
Image Segmentation (HP)
|
100% |
18334
297.2 IPS |
|
Image Segmentation (Q)
|
99% |
24106
390.8 IPS |
|
Pose Estimation (SP)
|
100% |
9331
10.9 IPS |
|
Pose Estimation (HP)
|
100% |
153426
179.0 IPS |
|
Pose Estimation (Q)
|
95% |
294955
345.7 IPS |
|
Object Detection (SP)
|
100% |
2329
184.7 IPS |
|
Object Detection (HP)
|
100% |
16279
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22714
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3895
46.3 IPS |
|
Face Detection (HP)
|
100% |
41193
489.5 IPS |
|
Face Detection (Q)
|
100% |
60330
716.9 IPS |
|
Depth Estimation (SP)
|
100% |
8320
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
95206
733.5 IPS |
|
Depth Estimation (Q)
|
85% |
159945
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20448
26.3 IPS |
|
Style Transfer (HP)
|
100% |
245467
315.6 IPS |
|
Style Transfer (Q)
|
96% |
302398
390.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5522
203.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
51082
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85975
3.17 KIPS |
|
Text Classification (SP)
|
100% |
3382
4.51 KIPS |
|
Text Classification (HP)
|
100% |
4406
5.88 KIPS |
|
Text Classification (Q)
|
93% |
4443
5.96 KIPS |
|
Machine Translation (SP)
|
100% |
4216
72.6 IPS |
|
Machine Translation (HP)
|
100% |
10305
177.5 IPS |
|
Machine Translation (Q)
|
98% |
11573
200.0 IPS |