User | Merlin12 |
Upload Date | April 14 2025 12:51 PM |
Views | 1 |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2074
385.7 IPS |
|
Image Classification (HP)
|
100% |
3031
563.6 IPS |
|
Image Classification (Q)
|
96% |
2171
405.4 IPS |
|
Image Segmentation (SP)
|
100% |
2272
36.8 IPS |
|
Image Segmentation (HP)
|
100% |
3437
55.7 IPS |
|
Image Segmentation (Q)
|
99% |
3898
63.2 IPS |
|
Pose Estimation (SP)
|
100% |
17318
20.2 IPS |
|
Pose Estimation (HP)
|
100% |
31591
36.9 IPS |
|
Pose Estimation (Q)
|
95% |
24615
28.9 IPS |
|
Object Detection (SP)
|
100% |
2498
198.2 IPS |
|
Object Detection (HP)
|
97% |
3822
304.3 IPS |
|
Object Detection (Q)
|
94% |
2652
211.4 IPS |
|
Face Detection (SP)
|
100% |
4745
56.4 IPS |
|
Face Detection (HP)
|
100% |
8026
95.4 IPS |
|
Face Detection (Q)
|
100% |
4690
55.7 IPS |
|
Depth Estimation (SP)
|
100% |
8627
66.5 IPS |
|
Depth Estimation (HP)
|
97% |
15387
118.9 IPS |
|
Depth Estimation (Q)
|
86% |
10767
84.0 IPS |
|
Style Transfer (SP)
|
100% |
26099
33.6 IPS |
|
Style Transfer (HP)
|
100% |
52482
67.5 IPS |
|
Style Transfer (Q)
|
96% |
40696
52.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5945
219.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
9951
367.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
5803
214.3 IPS |
|
Text Classification (SP)
|
100% |
2914
3.89 KIPS |
|
Text Classification (HP)
|
100% |
5181
6.92 KIPS |
|
Text Classification (Q)
|
93% |
5153
6.92 KIPS |
|
Machine Translation (SP)
|
100% |
5615
96.7 IPS |
|
Machine Translation (HP)
|
98% |
8705
150.4 IPS |
|
Machine Translation (Q)
|
98% |
8848
152.9 IPS |