Upload Date | April 23 2025 08:26 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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 | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2110
392.4 IPS |
|
Image Classification (HP)
|
100% |
17188
3.20 KIPS |
|
Image Classification (Q)
|
99% |
17919
3.34 KIPS |
|
Image Segmentation (SP)
|
100% |
2401
38.9 IPS |
|
Image Segmentation (HP)
|
100% |
17371
281.6 IPS |
|
Image Segmentation (Q)
|
100% |
17259
279.8 IPS |
|
Pose Estimation (SP)
|
100% |
17806
20.8 IPS |
|
Pose Estimation (HP)
|
100% |
119223
139.1 IPS |
|
Pose Estimation (Q)
|
94% |
223305
261.9 IPS |
|
Object Detection (SP)
|
100% |
2548
202.1 IPS |
|
Object Detection (HP)
|
100% |
17414
1.38 KIPS |
|
Object Detection (Q)
|
91% |
24937
1.99 KIPS |
|
Face Detection (SP)
|
100% |
4810
57.1 IPS |
|
Face Detection (HP)
|
100% |
27065
321.6 IPS |
|
Face Detection (Q)
|
100% |
46071
547.4 IPS |
|
Depth Estimation (SP)
|
100% |
8825
68.0 IPS |
|
Depth Estimation (HP)
|
99% |
89166
687.0 IPS |
|
Depth Estimation (Q)
|
97% |
93206
720.7 IPS |
|
Style Transfer (SP)
|
100% |
26625
34.2 IPS |
|
Style Transfer (HP)
|
100% |
167807
215.7 IPS |
|
Style Transfer (Q)
|
100% |
167593
215.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
6095
225.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
45920
1.70 KIPS |
|
Image Super-Resolution (Q)
|
98% |
78278
2.90 KIPS |
|
Text Classification (SP)
|
100% |
2949
3.94 KIPS |
|
Text Classification (HP)
|
100% |
6076
8.11 KIPS |
|
Text Classification (Q)
|
93% |
6511
8.74 KIPS |
|
Machine Translation (SP)
|
100% |
6014
103.6 IPS |
|
Machine Translation (HP)
|
100% |
17015
293.1 IPS |
|
Machine Translation (Q)
|
98% |
17022
294.2 IPS |