User | iantm |
Upload Date | August 15 2025 04:37 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 26.0 |
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 | 7.46 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2011
374.0 IPS |
|
Image Classification (HP)
|
100% |
14228
2.65 KIPS |
|
Image Classification (Q)
|
97% |
17834
3.33 KIPS |
|
Image Segmentation (SP)
|
100% |
1870
30.3 IPS |
|
Image Segmentation (HP)
|
100% |
18159
294.4 IPS |
|
Image Segmentation (Q)
|
99% |
23731
384.7 IPS |
|
Pose Estimation (SP)
|
100% |
9452
11.0 IPS |
|
Pose Estimation (HP)
|
100% |
152333
177.7 IPS |
|
Pose Estimation (Q)
|
95% |
293106
343.5 IPS |
|
Object Detection (SP)
|
100% |
2356
186.9 IPS |
|
Object Detection (HP)
|
100% |
16078
1.28 KIPS |
|
Object Detection (Q)
|
91% |
21685
1.73 KIPS |
|
Face Detection (SP)
|
100% |
3752
44.6 IPS |
|
Face Detection (HP)
|
100% |
40072
476.1 IPS |
|
Face Detection (Q)
|
100% |
53306
633.4 IPS |
|
Depth Estimation (SP)
|
100% |
8294
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
93907
723.5 IPS |
|
Depth Estimation (Q)
|
85% |
158264
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
23550
30.3 IPS |
|
Style Transfer (HP)
|
100% |
245640
315.8 IPS |
|
Style Transfer (Q)
|
96% |
295748
381.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5850
216.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
51069
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79435
2.93 KIPS |
|
Text Classification (SP)
|
100% |
3673
4.90 KIPS |
|
Text Classification (HP)
|
99% |
6131
8.18 KIPS |
|
Text Classification (Q)
|
93% |
6544
8.78 KIPS |
|
Machine Translation (SP)
|
100% |
4247
73.2 IPS |
|
Machine Translation (HP)
|
100% |
11289
194.5 IPS |
|
Machine Translation (Q)
|
98% |
13059
225.7 IPS |