User | Motoshige |
Upload Date | March 18 2025 05:03 PM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
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% |
2074
385.8 IPS |
|
Image Classification (HP)
|
100% |
17920
3.33 KIPS |
|
Image Classification (Q)
|
97% |
23372
4.36 KIPS |
|
Image Segmentation (SP)
|
100% |
2483
40.3 IPS |
|
Image Segmentation (HP)
|
100% |
23253
376.9 IPS |
|
Image Segmentation (Q)
|
99% |
32080
520.0 IPS |
|
Pose Estimation (SP)
|
100% |
18972
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123348
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
231123
270.9 IPS |
|
Object Detection (SP)
|
100% |
2475
196.3 IPS |
|
Object Detection (HP)
|
100% |
19366
1.54 KIPS |
|
Object Detection (Q)
|
91% |
24178
1.93 KIPS |
|
Face Detection (SP)
|
100% |
4590
54.5 IPS |
|
Face Detection (HP)
|
100% |
41735
495.9 IPS |
|
Face Detection (Q)
|
100% |
56081
666.4 IPS |
|
Depth Estimation (SP)
|
100% |
8775
67.6 IPS |
|
Depth Estimation (HP)
|
99% |
111629
860.0 IPS |
|
Depth Estimation (Q)
|
85% |
177444
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35471
45.6 IPS |
|
Style Transfer (HP)
|
100% |
237674
305.5 IPS |
|
Style Transfer (Q)
|
96% |
302234
390.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7039
259.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46525
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78750
2.91 KIPS |
|
Text Classification (SP)
|
100% |
2936
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5285
7.05 KIPS |
|
Text Classification (Q)
|
93% |
4869
6.53 KIPS |
|
Machine Translation (SP)
|
100% |
5817
100.2 IPS |
|
Machine Translation (HP)
|
100% |
16354
281.7 IPS |
|
Machine Translation (Q)
|
98% |
16740
289.3 IPS |