User | edsonchan |
Upload Date | May 19 2025 06:23 AM |
Views | 4 |
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 | 4.49 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2064
383.8 IPS |
|
Image Classification (HP)
|
100% |
17470
3.25 KIPS |
|
Image Classification (Q)
|
97% |
22365
4.17 KIPS |
|
Image Segmentation (SP)
|
100% |
2294
37.2 IPS |
|
Image Segmentation (HP)
|
100% |
23284
377.5 IPS |
|
Image Segmentation (Q)
|
99% |
32295
523.5 IPS |
|
Pose Estimation (SP)
|
100% |
17404
20.3 IPS |
|
Pose Estimation (HP)
|
100% |
122780
143.3 IPS |
|
Pose Estimation (Q)
|
95% |
228788
268.2 IPS |
|
Object Detection (SP)
|
100% |
2495
197.9 IPS |
|
Object Detection (HP)
|
100% |
20017
1.59 KIPS |
|
Object Detection (Q)
|
91% |
23948
1.91 KIPS |
|
Face Detection (SP)
|
100% |
4734
56.3 IPS |
|
Face Detection (HP)
|
100% |
45705
543.1 IPS |
|
Face Detection (Q)
|
100% |
63694
756.8 IPS |
|
Depth Estimation (SP)
|
100% |
8614
66.4 IPS |
|
Depth Estimation (HP)
|
99% |
112603
867.5 IPS |
|
Depth Estimation (Q)
|
85% |
177752
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
26162
33.6 IPS |
|
Style Transfer (HP)
|
100% |
239188
307.5 IPS |
|
Style Transfer (Q)
|
96% |
298541
385.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5967
220.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
47515
1.75 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80827
2.98 KIPS |
|
Text Classification (SP)
|
100% |
2878
3.84 KIPS |
|
Text Classification (HP)
|
100% |
5516
7.36 KIPS |
|
Text Classification (Q)
|
93% |
5652
7.59 KIPS |
|
Machine Translation (SP)
|
100% |
5596
96.4 IPS |
|
Machine Translation (HP)
|
100% |
16637
286.6 IPS |
|
Machine Translation (Q)
|
98% |
16721
289.0 IPS |