| Upload Date | May 07 2025 02:19 AM |
| Views | 3 |
| 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% |
2082
387.3 IPS |
|
|
Image Classification (HP)
|
100% |
15208
2.83 KIPS |
|
|
Image Classification (Q)
|
97% |
20522
3.83 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1956
31.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
18302
296.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
24069
390.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
8706
10.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
147775
172.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
291444
341.6 IPS |
|
|
Object Detection (SP)
|
100% |
2312
183.4 IPS |
|
|
Object Detection (HP)
|
100% |
16293
1.29 KIPS |
|
|
Object Detection (Q)
|
91% |
22898
1.83 KIPS |
|
|
Face Detection (SP)
|
100% |
3835
45.6 IPS |
|
|
Face Detection (HP)
|
100% |
41247
490.1 IPS |
|
|
Face Detection (Q)
|
100% |
58441
694.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7998
61.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
95062
732.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
159603
1.25 KIPS |
|
|
Style Transfer (SP)
|
100% |
19209
24.7 IPS |
|
|
Style Transfer (HP)
|
100% |
244473
314.3 IPS |
|
|
Style Transfer (Q)
|
96% |
303125
391.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5100
188.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
49857
1.84 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
83931
3.10 KIPS |
|
|
Text Classification (SP)
|
100% |
3379
4.51 KIPS |
|
|
Text Classification (HP)
|
100% |
4925
6.57 KIPS |
|
|
Text Classification (Q)
|
93% |
4792
6.43 KIPS |
|
|
Machine Translation (SP)
|
100% |
4238
73.0 IPS |
|
|
Machine Translation (HP)
|
100% |
10199
175.7 IPS |
|
|
Machine Translation (Q)
|
98% |
11462
198.1 IPS |