User | rafaexnexus |
Upload Date | June 01 2025 09:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1678
312.0 IPS |
|
Image Classification (HP)
|
100% |
10926
2.03 KIPS |
|
Image Classification (Q)
|
97% |
15621
2.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1585
25.7 IPS |
|
Image Segmentation (HP)
|
100% |
16793
272.2 IPS |
|
Image Segmentation (Q)
|
99% |
21503
348.6 IPS |
|
Pose Estimation (SP)
|
100% |
8127
9.48 IPS |
|
Pose Estimation (HP)
|
100% |
105886
123.6 IPS |
|
Pose Estimation (Q)
|
95% |
204369
239.5 IPS |
|
Object Detection (SP)
|
100% |
1798
142.6 IPS |
|
Object Detection (HP)
|
100% |
13758
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19214
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3148
37.4 IPS |
|
Face Detection (HP)
|
100% |
36564
434.5 IPS |
|
Face Detection (Q)
|
100% |
52648
625.6 IPS |
|
Depth Estimation (SP)
|
100% |
7096
54.7 IPS |
|
Depth Estimation (HP)
|
99% |
78451
604.4 IPS |
|
Depth Estimation (Q)
|
85% |
127330
995.5 IPS |
|
Style Transfer (SP)
|
100% |
21887
28.1 IPS |
|
Style Transfer (HP)
|
100% |
207627
266.9 IPS |
|
Style Transfer (Q)
|
96% |
255970
330.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5029
185.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
33929
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
61039
2.25 KIPS |
|
Text Classification (SP)
|
100% |
3238
4.32 KIPS |
|
Text Classification (HP)
|
100% |
3226
4.31 KIPS |
|
Text Classification (Q)
|
93% |
3432
4.61 KIPS |
|
Machine Translation (SP)
|
100% |
3169
54.6 IPS |
|
Machine Translation (HP)
|
100% |
6512
112.2 IPS |
|
Machine Translation (Q)
|
98% |
7426
128.3 IPS |