Upload Date | September 02 2025 02:40 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2097
389.9 IPS |
|
Image Classification (HP)
|
100% |
15133
2.81 KIPS |
|
Image Classification (Q)
|
97% |
20037
3.74 KIPS |
|
Image Segmentation (SP)
|
100% |
2020
32.7 IPS |
|
Image Segmentation (HP)
|
100% |
18348
297.4 IPS |
|
Image Segmentation (Q)
|
99% |
24108
390.8 IPS |
|
Pose Estimation (SP)
|
100% |
10174
11.9 IPS |
|
Pose Estimation (HP)
|
100% |
153462
179.1 IPS |
|
Pose Estimation (Q)
|
95% |
293063
343.5 IPS |
|
Object Detection (SP)
|
100% |
2396
190.1 IPS |
|
Object Detection (HP)
|
100% |
16114
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22217
1.78 KIPS |
|
Face Detection (SP)
|
100% |
4037
48.0 IPS |
|
Face Detection (HP)
|
100% |
39671
471.4 IPS |
|
Face Detection (Q)
|
100% |
56219
668.0 IPS |
|
Depth Estimation (SP)
|
100% |
8517
65.6 IPS |
|
Depth Estimation (HP)
|
99% |
95373
734.8 IPS |
|
Depth Estimation (Q)
|
85% |
163402
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
22540
29.0 IPS |
|
Style Transfer (HP)
|
100% |
244633
314.5 IPS |
|
Style Transfer (Q)
|
96% |
301356
388.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
6105
225.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
51069
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85498
3.16 KIPS |
|
Text Classification (SP)
|
100% |
3442
4.59 KIPS |
|
Text Classification (HP)
|
100% |
4861
6.49 KIPS |
|
Text Classification (Q)
|
93% |
5849
7.85 KIPS |
|
Machine Translation (SP)
|
100% |
4317
74.4 IPS |
|
Machine Translation (HP)
|
100% |
10237
176.3 IPS |
|
Machine Translation (Q)
|
98% |
11463
198.1 IPS |