User | everestsky |
Upload Date | May 20 2025 01:35 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D2059) |
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 | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2127
395.6 IPS |
|
Image Classification (HP)
|
100% |
3048
566.7 IPS |
|
Image Classification (Q)
|
96% |
2199
410.6 IPS |
|
Image Segmentation (SP)
|
100% |
2542
41.2 IPS |
|
Image Segmentation (HP)
|
100% |
3672
59.5 IPS |
|
Image Segmentation (Q)
|
99% |
3964
64.3 IPS |
|
Pose Estimation (SP)
|
100% |
19192
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
32306
37.7 IPS |
|
Pose Estimation (Q)
|
95% |
24867
29.1 IPS |
|
Object Detection (SP)
|
100% |
2590
205.4 IPS |
|
Object Detection (HP)
|
97% |
3889
309.6 IPS |
|
Object Detection (Q)
|
94% |
2703
215.5 IPS |
|
Face Detection (SP)
|
100% |
4818
57.2 IPS |
|
Face Detection (HP)
|
100% |
8225
97.7 IPS |
|
Face Detection (Q)
|
100% |
4763
56.6 IPS |
|
Depth Estimation (SP)
|
100% |
9088
70.0 IPS |
|
Depth Estimation (HP)
|
97% |
15195
117.5 IPS |
|
Depth Estimation (Q)
|
86% |
10559
82.4 IPS |
|
Style Transfer (SP)
|
100% |
37242
47.9 IPS |
|
Style Transfer (HP)
|
100% |
53014
68.2 IPS |
|
Style Transfer (Q)
|
96% |
40297
52.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7188
265.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
9644
356.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
5307
195.9 IPS |
|
Text Classification (SP)
|
100% |
2966
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5479
7.31 KIPS |
|
Text Classification (Q)
|
93% |
5303
7.12 KIPS |
|
Machine Translation (SP)
|
100% |
6031
103.9 IPS |
|
Machine Translation (HP)
|
98% |
8993
155.4 IPS |
|
Machine Translation (Q)
|
98% |
8987
155.3 IPS |