User | M91 |
Upload Date | September 20 2025 03:19 AM |
Views | 2 |
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% |
1550
288.3 IPS |
|
Image Classification (HP)
|
100% |
11551
2.15 KIPS |
|
Image Classification (Q)
|
97% |
14494
2.70 KIPS |
|
Image Segmentation (SP)
|
100% |
1562
25.3 IPS |
|
Image Segmentation (HP)
|
100% |
16582
268.8 IPS |
|
Image Segmentation (Q)
|
99% |
21241
344.3 IPS |
|
Pose Estimation (SP)
|
100% |
7019
8.19 IPS |
|
Pose Estimation (HP)
|
100% |
104751
122.2 IPS |
|
Pose Estimation (Q)
|
95% |
202715
237.6 IPS |
|
Object Detection (SP)
|
100% |
1640
130.1 IPS |
|
Object Detection (HP)
|
100% |
13130
1.04 KIPS |
|
Object Detection (Q)
|
91% |
17132
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3082
36.6 IPS |
|
Face Detection (HP)
|
100% |
34349
408.1 IPS |
|
Face Detection (Q)
|
100% |
47548
565.0 IPS |
|
Depth Estimation (SP)
|
100% |
6754
52.0 IPS |
|
Depth Estimation (HP)
|
99% |
72258
556.7 IPS |
|
Depth Estimation (Q)
|
85% |
111636
872.8 IPS |
|
Style Transfer (SP)
|
100% |
20428
26.3 IPS |
|
Style Transfer (HP)
|
100% |
199428
256.4 IPS |
|
Style Transfer (Q)
|
96% |
242826
313.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4519
166.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
29769
1.10 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56224
2.08 KIPS |
|
Text Classification (SP)
|
100% |
3386
4.52 KIPS |
|
Text Classification (HP)
|
99% |
5913
7.89 KIPS |
|
Text Classification (Q)
|
93% |
5873
7.88 KIPS |
|
Machine Translation (SP)
|
100% |
3178
54.7 IPS |
|
Machine Translation (HP)
|
100% |
5860
100.9 IPS |
|
Machine Translation (Q)
|
98% |
6415
110.9 IPS |