User | edsonchan |
Upload Date | May 15 2025 11:12 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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% |
2084
387.5 IPS |
|
Image Classification (HP)
|
100% |
17607
3.27 KIPS |
|
Image Classification (Q)
|
97% |
24339
4.54 KIPS |
|
Image Segmentation (SP)
|
100% |
2286
37.1 IPS |
|
Image Segmentation (HP)
|
100% |
23303
377.8 IPS |
|
Image Segmentation (Q)
|
99% |
32809
531.9 IPS |
|
Pose Estimation (SP)
|
100% |
17086
19.9 IPS |
|
Pose Estimation (HP)
|
100% |
122797
143.3 IPS |
|
Pose Estimation (Q)
|
95% |
230259
269.9 IPS |
|
Object Detection (SP)
|
100% |
2463
195.4 IPS |
|
Object Detection (HP)
|
100% |
20364
1.62 KIPS |
|
Object Detection (Q)
|
91% |
24824
1.98 KIPS |
|
Face Detection (SP)
|
100% |
4664
55.4 IPS |
|
Face Detection (HP)
|
100% |
45999
546.6 IPS |
|
Face Detection (Q)
|
100% |
55936
664.6 IPS |
|
Depth Estimation (SP)
|
100% |
8622
66.4 IPS |
|
Depth Estimation (HP)
|
99% |
106990
824.3 IPS |
|
Depth Estimation (Q)
|
85% |
177920
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
25753
33.1 IPS |
|
Style Transfer (HP)
|
100% |
237193
304.9 IPS |
|
Style Transfer (Q)
|
96% |
302539
390.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5972
220.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
47616
1.76 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80315
2.97 KIPS |
|
Text Classification (SP)
|
100% |
2910
3.88 KIPS |
|
Text Classification (HP)
|
100% |
6132
8.18 KIPS |
|
Text Classification (Q)
|
93% |
5423
7.28 KIPS |
|
Machine Translation (SP)
|
100% |
5688
98.0 IPS |
|
Machine Translation (HP)
|
100% |
16578
285.6 IPS |
|
Machine Translation (Q)
|
98% |
17274
298.5 IPS |