User | M91 |
Upload Date | August 12 2025 01:56 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1675
311.5 IPS |
|
Image Classification (HP)
|
100% |
10907
2.03 KIPS |
|
Image Classification (Q)
|
97% |
15593
2.91 KIPS |
|
Image Segmentation (SP)
|
100% |
1598
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15736
255.1 IPS |
|
Image Segmentation (Q)
|
99% |
21158
343.0 IPS |
|
Pose Estimation (SP)
|
100% |
7616
8.89 IPS |
|
Pose Estimation (HP)
|
100% |
104860
122.4 IPS |
|
Pose Estimation (Q)
|
95% |
206782
242.4 IPS |
|
Object Detection (SP)
|
100% |
1755
139.2 IPS |
|
Object Detection (HP)
|
100% |
13861
1.10 KIPS |
|
Object Detection (Q)
|
91% |
17223
1.38 KIPS |
|
Face Detection (SP)
|
100% |
3141
37.3 IPS |
|
Face Detection (HP)
|
100% |
34218
406.6 IPS |
|
Face Detection (Q)
|
100% |
51869
616.3 IPS |
|
Depth Estimation (SP)
|
100% |
6840
52.7 IPS |
|
Depth Estimation (HP)
|
99% |
78190
602.4 IPS |
|
Depth Estimation (Q)
|
85% |
123041
962.0 IPS |
|
Style Transfer (SP)
|
100% |
20664
26.6 IPS |
|
Style Transfer (HP)
|
100% |
205752
264.5 IPS |
|
Style Transfer (Q)
|
96% |
248797
321.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4704
173.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
34404
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57327
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3218
4.30 KIPS |
|
Text Classification (HP)
|
99% |
5554
7.41 KIPS |
|
Text Classification (Q)
|
93% |
5542
7.44 KIPS |
|
Machine Translation (SP)
|
100% |
3277
56.5 IPS |
|
Machine Translation (HP)
|
100% |
6529
112.5 IPS |
|
Machine Translation (Q)
|
98% |
7150
123.6 IPS |