User | RAMFlux |
Upload Date | April 01 2025 09:57 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
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% |
2075
385.9 IPS |
|
Image Classification (HP)
|
100% |
15232
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20532
3.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1963
31.8 IPS |
|
Image Segmentation (HP)
|
100% |
18303
296.7 IPS |
|
Image Segmentation (Q)
|
99% |
24126
391.1 IPS |
|
Pose Estimation (SP)
|
100% |
8955
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
152043
177.4 IPS |
|
Pose Estimation (Q)
|
95% |
290570
340.6 IPS |
|
Object Detection (SP)
|
100% |
2331
184.9 IPS |
|
Object Detection (HP)
|
100% |
16106
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22970
1.84 KIPS |
|
Face Detection (SP)
|
100% |
3884
46.1 IPS |
|
Face Detection (HP)
|
100% |
41186
489.4 IPS |
|
Face Detection (Q)
|
100% |
58488
695.0 IPS |
|
Depth Estimation (SP)
|
100% |
8138
62.7 IPS |
|
Depth Estimation (HP)
|
99% |
95011
732.0 IPS |
|
Depth Estimation (Q)
|
85% |
159786
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
19764
25.4 IPS |
|
Style Transfer (HP)
|
100% |
245414
315.5 IPS |
|
Style Transfer (Q)
|
96% |
303506
391.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5428
200.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
49787
1.84 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83180
3.07 KIPS |
|
Text Classification (SP)
|
100% |
3408
4.55 KIPS |
|
Text Classification (HP)
|
100% |
4536
6.05 KIPS |
|
Text Classification (Q)
|
93% |
4834
6.49 KIPS |
|
Machine Translation (SP)
|
100% |
4123
71.0 IPS |
|
Machine Translation (HP)
|
100% |
9862
169.9 IPS |
|
Machine Translation (Q)
|
98% |
11047
190.9 IPS |