User | markbyrn |
Upload Date | July 01 2025 03:18 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.38 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2100
390.5 IPS |
|
Image Classification (HP)
|
100% |
3049
566.9 IPS |
|
Image Classification (Q)
|
96% |
2149
401.3 IPS |
|
Image Segmentation (SP)
|
100% |
2376
38.5 IPS |
|
Image Segmentation (HP)
|
100% |
3514
57.0 IPS |
|
Image Segmentation (Q)
|
99% |
3902
63.3 IPS |
|
Pose Estimation (SP)
|
100% |
17731
20.7 IPS |
|
Pose Estimation (HP)
|
100% |
32668
38.1 IPS |
|
Pose Estimation (Q)
|
95% |
24871
29.2 IPS |
|
Object Detection (SP)
|
100% |
2505
198.7 IPS |
|
Object Detection (HP)
|
97% |
3910
311.3 IPS |
|
Object Detection (Q)
|
94% |
2713
216.2 IPS |
|
Face Detection (SP)
|
100% |
4669
55.5 IPS |
|
Face Detection (HP)
|
100% |
8137
96.7 IPS |
|
Face Detection (Q)
|
100% |
4570
54.3 IPS |
|
Depth Estimation (SP)
|
100% |
8552
65.9 IPS |
|
Depth Estimation (HP)
|
97% |
15141
117.0 IPS |
|
Depth Estimation (Q)
|
86% |
10477
81.8 IPS |
|
Style Transfer (SP)
|
100% |
26952
34.6 IPS |
|
Style Transfer (HP)
|
100% |
52495
67.5 IPS |
|
Style Transfer (Q)
|
96% |
39942
51.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5973
220.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
9941
367.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
6052
223.5 IPS |
|
Text Classification (SP)
|
100% |
2889
3.86 KIPS |
|
Text Classification (HP)
|
100% |
5305
7.08 KIPS |
|
Text Classification (Q)
|
93% |
5126
6.88 KIPS |
|
Machine Translation (SP)
|
100% |
5745
99.0 IPS |
|
Machine Translation (HP)
|
98% |
9288
160.5 IPS |
|
Machine Translation (Q)
|
98% |
9271
160.2 IPS |