User | edsonchan |
Upload Date | May 19 2025 06:19 AM |
Views | 7 |
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 | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2076
386.0 IPS |
|
Image Classification (HP)
|
100% |
3044
566.0 IPS |
|
Image Classification (Q)
|
96% |
2190
409.0 IPS |
|
Image Segmentation (SP)
|
100% |
2368
38.4 IPS |
|
Image Segmentation (HP)
|
100% |
3713
60.2 IPS |
|
Image Segmentation (Q)
|
99% |
3905
63.3 IPS |
|
Pose Estimation (SP)
|
100% |
17325
20.2 IPS |
|
Pose Estimation (HP)
|
100% |
31958
37.3 IPS |
|
Pose Estimation (Q)
|
95% |
24083
28.2 IPS |
|
Object Detection (SP)
|
100% |
2474
196.2 IPS |
|
Object Detection (HP)
|
97% |
3849
306.4 IPS |
|
Object Detection (Q)
|
94% |
2687
214.2 IPS |
|
Face Detection (SP)
|
100% |
4648
55.2 IPS |
|
Face Detection (HP)
|
100% |
7746
92.0 IPS |
|
Face Detection (Q)
|
100% |
4658
55.4 IPS |
|
Depth Estimation (SP)
|
100% |
8654
66.7 IPS |
|
Depth Estimation (HP)
|
97% |
14079
108.8 IPS |
|
Depth Estimation (Q)
|
86% |
10058
78.5 IPS |
|
Style Transfer (SP)
|
100% |
25921
33.3 IPS |
|
Style Transfer (HP)
|
100% |
50642
65.1 IPS |
|
Style Transfer (Q)
|
96% |
38354
49.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
6032
222.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
10251
378.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
5790
213.8 IPS |
|
Text Classification (SP)
|
100% |
2915
3.89 KIPS |
|
Text Classification (HP)
|
100% |
5287
7.06 KIPS |
|
Text Classification (Q)
|
93% |
5277
7.08 KIPS |
|
Machine Translation (SP)
|
100% |
5639
97.1 IPS |
|
Machine Translation (HP)
|
98% |
9276
160.3 IPS |
|
Machine Translation (Q)
|
98% |
9299
160.7 IPS |