User | edsonchan |
Upload Date | May 20 2025 06:27 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
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 | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2035
378.4 IPS |
|
Image Classification (HP)
|
100% |
3065
570.0 IPS |
|
Image Classification (Q)
|
96% |
2178
406.8 IPS |
|
Image Segmentation (SP)
|
100% |
2355
38.2 IPS |
|
Image Segmentation (HP)
|
100% |
3663
59.4 IPS |
|
Image Segmentation (Q)
|
99% |
3914
63.4 IPS |
|
Pose Estimation (SP)
|
100% |
17119
20.0 IPS |
|
Pose Estimation (HP)
|
100% |
31476
36.7 IPS |
|
Pose Estimation (Q)
|
95% |
24078
28.2 IPS |
|
Object Detection (SP)
|
100% |
2474
196.3 IPS |
|
Object Detection (HP)
|
97% |
3838
305.6 IPS |
|
Object Detection (Q)
|
94% |
2676
213.3 IPS |
|
Face Detection (SP)
|
100% |
4616
54.8 IPS |
|
Face Detection (HP)
|
100% |
7761
92.2 IPS |
|
Face Detection (Q)
|
100% |
4611
54.8 IPS |
|
Depth Estimation (SP)
|
100% |
8616
66.4 IPS |
|
Depth Estimation (HP)
|
97% |
14135
109.3 IPS |
|
Depth Estimation (Q)
|
86% |
10017
78.2 IPS |
|
Style Transfer (SP)
|
100% |
25599
32.9 IPS |
|
Style Transfer (HP)
|
100% |
49875
64.1 IPS |
|
Style Transfer (Q)
|
96% |
38882
50.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5964
220.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
9619
355.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
5714
211.0 IPS |
|
Text Classification (SP)
|
100% |
2904
3.88 KIPS |
|
Text Classification (HP)
|
100% |
5257
7.02 KIPS |
|
Text Classification (Q)
|
93% |
5253
7.05 KIPS |
|
Machine Translation (SP)
|
100% |
5640
97.1 IPS |
|
Machine Translation (HP)
|
98% |
9131
157.8 IPS |
|
Machine Translation (Q)
|
98% |
9245
159.8 IPS |