User | ioanton |
Upload Date | April 21 2025 06:09 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | Mac16,9 |
Model ID | Mac16,9 |
Motherboard | Mac16,9 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2134
396.8 IPS |
|
Image Classification (HP)
|
100% |
3105
577.4 IPS |
|
Image Classification (Q)
|
96% |
2195
409.9 IPS |
|
Image Segmentation (SP)
|
100% |
2369
38.4 IPS |
|
Image Segmentation (HP)
|
100% |
3685
59.7 IPS |
|
Image Segmentation (Q)
|
99% |
3957
64.1 IPS |
|
Pose Estimation (SP)
|
100% |
18235
21.3 IPS |
|
Pose Estimation (HP)
|
100% |
32536
38.0 IPS |
|
Pose Estimation (Q)
|
95% |
24945
29.2 IPS |
|
Object Detection (SP)
|
100% |
2641
209.5 IPS |
|
Object Detection (HP)
|
97% |
3892
309.8 IPS |
|
Object Detection (Q)
|
94% |
2693
214.7 IPS |
|
Face Detection (SP)
|
100% |
4888
58.1 IPS |
|
Face Detection (HP)
|
100% |
8083
96.0 IPS |
|
Face Detection (Q)
|
100% |
4684
55.7 IPS |
|
Depth Estimation (SP)
|
100% |
8860
68.3 IPS |
|
Depth Estimation (HP)
|
97% |
14896
115.2 IPS |
|
Depth Estimation (Q)
|
86% |
10422
81.3 IPS |
|
Style Transfer (SP)
|
100% |
25658
33.0 IPS |
|
Style Transfer (HP)
|
100% |
53285
68.5 IPS |
|
Style Transfer (Q)
|
96% |
39960
51.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
6088
224.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
10162
375.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
5984
221.0 IPS |
|
Text Classification (SP)
|
100% |
2921
3.90 KIPS |
|
Text Classification (HP)
|
100% |
5537
7.39 KIPS |
|
Text Classification (Q)
|
93% |
5463
7.33 KIPS |
|
Machine Translation (SP)
|
100% |
6257
107.8 IPS |
|
Machine Translation (HP)
|
98% |
9380
162.1 IPS |
|
Machine Translation (Q)
|
98% |
9489
164.0 IPS |