User | wirsich |
Upload Date | August 24 2025 03:30 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2069
384.8 IPS |
|
Image Classification (HP)
|
100% |
3035
564.5 IPS |
|
Image Classification (Q)
|
96% |
2167
404.6 IPS |
|
Image Segmentation (SP)
|
100% |
2288
37.1 IPS |
|
Image Segmentation (HP)
|
100% |
3356
54.4 IPS |
|
Image Segmentation (Q)
|
99% |
3899
63.2 IPS |
|
Pose Estimation (SP)
|
100% |
17227
20.1 IPS |
|
Pose Estimation (HP)
|
100% |
32674
38.1 IPS |
|
Pose Estimation (Q)
|
95% |
24769
29.0 IPS |
|
Object Detection (SP)
|
100% |
2495
197.9 IPS |
|
Object Detection (HP)
|
97% |
3815
303.7 IPS |
|
Object Detection (Q)
|
94% |
2662
212.2 IPS |
|
Face Detection (SP)
|
100% |
4732
56.2 IPS |
|
Face Detection (HP)
|
100% |
8113
96.4 IPS |
|
Face Detection (Q)
|
100% |
4686
55.7 IPS |
|
Depth Estimation (SP)
|
100% |
8643
66.6 IPS |
|
Depth Estimation (HP)
|
97% |
14646
113.2 IPS |
|
Depth Estimation (Q)
|
86% |
10469
81.7 IPS |
|
Style Transfer (SP)
|
100% |
25685
33.0 IPS |
|
Style Transfer (HP)
|
100% |
51905
66.7 IPS |
|
Style Transfer (Q)
|
96% |
40247
51.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5971
220.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
9954
367.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
5573
205.8 IPS |
|
Text Classification (SP)
|
100% |
2891
3.86 KIPS |
|
Text Classification (HP)
|
100% |
5260
7.02 KIPS |
|
Text Classification (Q)
|
93% |
5212
7.00 KIPS |
|
Machine Translation (SP)
|
100% |
5607
96.6 IPS |
|
Machine Translation (HP)
|
98% |
8937
154.4 IPS |
|
Machine Translation (Q)
|
98% |
8949
154.7 IPS |