| User | toygoon |
| Upload Date | February 12 2025 08:42 AM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.3.1 |
| 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% |
2735
508.7 IPS |
|
|
Image Classification (HP)
|
100% |
2668
496.2 IPS |
|
|
Image Classification (Q)
|
97% |
2929
546.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
3478
56.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
4523
73.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
4481
72.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
15840
18.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
16495
19.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
15662
18.4 IPS |
|
|
Object Detection (SP)
|
100% |
3270
259.4 IPS |
|
|
Object Detection (HP)
|
100% |
3610
286.3 IPS |
|
|
Object Detection (Q)
|
91% |
2824
225.7 IPS |
|
|
Face Detection (SP)
|
100% |
7817
92.9 IPS |
|
|
Face Detection (HP)
|
100% |
10930
129.9 IPS |
|
|
Face Detection (Q)
|
100% |
7261
86.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
13538
104.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
14760
113.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
12795
100.0 IPS |
|
|
Style Transfer (SP)
|
100% |
33164
42.6 IPS |
|
|
Style Transfer (HP)
|
100% |
37924
48.8 IPS |
|
|
Style Transfer (Q)
|
96% |
37220
48.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
8100
299.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8491
313.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6925
255.7 IPS |
|
|
Text Classification (SP)
|
100% |
3413
4.56 KIPS |
|
|
Text Classification (HP)
|
100% |
5853
7.81 KIPS |
|
|
Text Classification (Q)
|
93% |
5829
7.82 KIPS |
|
|
Machine Translation (SP)
|
100% |
860
14.8 IPS |
|
|
Machine Translation (HP)
|
100% |
966
16.6 IPS |
|
|
Machine Translation (Q)
|
98% |
936
16.2 IPS |