User | vuthi |
Upload Date | September 24 2025 02:56 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A354) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2146
399.1 IPS |
|
Image Classification (HP)
|
100% |
3062
569.5 IPS |
|
Image Classification (Q)
|
96% |
2118
395.6 IPS |
|
Image Segmentation (SP)
|
100% |
2283
37.0 IPS |
|
Image Segmentation (HP)
|
100% |
3362
54.5 IPS |
|
Image Segmentation (Q)
|
99% |
3828
62.1 IPS |
|
Pose Estimation (SP)
|
100% |
17312
20.2 IPS |
|
Pose Estimation (HP)
|
100% |
34196
39.9 IPS |
|
Pose Estimation (Q)
|
95% |
26630
31.2 IPS |
|
Object Detection (SP)
|
100% |
2562
203.2 IPS |
|
Object Detection (HP)
|
97% |
3875
308.5 IPS |
|
Object Detection (Q)
|
94% |
2743
218.7 IPS |
|
Face Detection (SP)
|
100% |
4958
58.9 IPS |
|
Face Detection (HP)
|
100% |
8539
101.5 IPS |
|
Face Detection (Q)
|
100% |
4680
55.6 IPS |
|
Depth Estimation (SP)
|
100% |
8722
67.2 IPS |
|
Depth Estimation (HP)
|
97% |
15237
117.8 IPS |
|
Depth Estimation (Q)
|
86% |
9561
74.6 IPS |
|
Style Transfer (SP)
|
100% |
30323
39.0 IPS |
|
Style Transfer (HP)
|
100% |
56671
72.9 IPS |
|
Style Transfer (Q)
|
96% |
43543
56.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7102
262.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
9193
339.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
5416
200.0 IPS |
|
Text Classification (SP)
|
100% |
3190
4.26 KIPS |
|
Text Classification (HP)
|
99% |
5617
7.50 KIPS |
|
Text Classification (Q)
|
93% |
5612
7.53 KIPS |
|
Machine Translation (SP)
|
100% |
5972
102.9 IPS |
|
Machine Translation (HP)
|
98% |
9537
164.8 IPS |
|
Machine Translation (Q)
|
98% |
9483
163.9 IPS |