User | Merlin12 |
Upload Date | April 14 2025 11:23 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E248) |
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 | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2043
379.9 IPS |
|
Image Classification (HP)
|
100% |
2970
552.3 IPS |
|
Image Classification (Q)
|
96% |
2121
396.1 IPS |
|
Image Segmentation (SP)
|
100% |
2260
36.6 IPS |
|
Image Segmentation (HP)
|
100% |
3432
55.6 IPS |
|
Image Segmentation (Q)
|
99% |
3828
62.1 IPS |
|
Pose Estimation (SP)
|
100% |
17078
19.9 IPS |
|
Pose Estimation (HP)
|
100% |
31657
36.9 IPS |
|
Pose Estimation (Q)
|
95% |
23902
28.0 IPS |
|
Object Detection (SP)
|
100% |
2439
193.5 IPS |
|
Object Detection (HP)
|
97% |
3738
297.6 IPS |
|
Object Detection (Q)
|
94% |
2624
209.1 IPS |
|
Face Detection (SP)
|
100% |
4625
55.0 IPS |
|
Face Detection (HP)
|
100% |
7806
92.8 IPS |
|
Face Detection (Q)
|
100% |
4667
55.5 IPS |
|
Depth Estimation (SP)
|
100% |
8571
66.0 IPS |
|
Depth Estimation (HP)
|
97% |
14901
115.2 IPS |
|
Depth Estimation (Q)
|
86% |
10477
81.8 IPS |
|
Style Transfer (SP)
|
100% |
26553
34.1 IPS |
|
Style Transfer (HP)
|
100% |
51418
66.1 IPS |
|
Style Transfer (Q)
|
96% |
39785
51.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5935
219.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
9886
365.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
5960
220.1 IPS |
|
Text Classification (SP)
|
100% |
2872
3.83 KIPS |
|
Text Classification (HP)
|
100% |
5136
6.86 KIPS |
|
Text Classification (Q)
|
93% |
5089
6.83 KIPS |
|
Machine Translation (SP)
|
100% |
5449
93.9 IPS |
|
Machine Translation (HP)
|
98% |
8712
150.5 IPS |
|
Machine Translation (Q)
|
98% |
8795
152.0 IPS |