User | iGeneration |
Upload Date | January 23 2025 08:48 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 3.79 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7434
1.38 KIPS |
|
Image Classification (HP)
|
100% |
8086
1.50 KIPS |
|
Image Classification (Q)
|
97% |
6709
1.25 KIPS |
|
Image Segmentation (SP)
|
100% |
10959
177.7 IPS |
|
Image Segmentation (HP)
|
100% |
11482
186.1 IPS |
|
Image Segmentation (Q)
|
99% |
11648
188.8 IPS |
|
Pose Estimation (SP)
|
100% |
46719
54.5 IPS |
|
Pose Estimation (HP)
|
100% |
48864
57.0 IPS |
|
Pose Estimation (Q)
|
95% |
46347
54.3 IPS |
|
Object Detection (SP)
|
100% |
7026
557.3 IPS |
|
Object Detection (HP)
|
100% |
7650
606.8 IPS |
|
Object Detection (Q)
|
91% |
6335
506.2 IPS |
|
Face Detection (SP)
|
100% |
23916
284.2 IPS |
|
Face Detection (HP)
|
100% |
25665
305.0 IPS |
|
Face Detection (Q)
|
100% |
18857
224.1 IPS |
|
Depth Estimation (SP)
|
100% |
32938
253.8 IPS |
|
Depth Estimation (HP)
|
99% |
34879
268.7 IPS |
|
Depth Estimation (Q)
|
85% |
29208
228.3 IPS |
|
Style Transfer (SP)
|
100% |
107016
137.6 IPS |
|
Style Transfer (HP)
|
100% |
116523
149.8 IPS |
|
Style Transfer (Q)
|
96% |
109990
141.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
18840
695.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
19971
737.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
15610
576.4 IPS |
|
Text Classification (SP)
|
100% |
2854
3.81 KIPS |
|
Text Classification (HP)
|
100% |
5336
7.12 KIPS |
|
Text Classification (Q)
|
93% |
5039
6.76 KIPS |
|
Machine Translation (SP)
|
100% |
1597
27.5 IPS |
|
Machine Translation (HP)
|
100% |
1878
32.3 IPS |
|
Machine Translation (Q)
|
98% |
1203
20.8 IPS |