User | dcjm |
Upload Date | November 12 2024 07:23 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5079e) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1552
288.6 IPS |
|
Image Classification (HP)
|
100% |
16045
2.98 KIPS |
|
Image Classification (Q)
|
97% |
17266
3.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1845
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
21850
354.2 IPS |
|
Image Segmentation (Q)
|
99% |
27053
438.5 IPS |
|
Pose Estimation (SP)
|
100% |
16729
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
120184
140.2 IPS |
|
Pose Estimation (Q)
|
95% |
118731
139.2 IPS |
|
Object Detection (SP)
|
100% |
1974
156.6 IPS |
|
Object Detection (HP)
|
100% |
17670
1.40 KIPS |
|
Object Detection (Q)
|
91% |
18882
1.51 KIPS |
|
Face Detection (SP)
|
100% |
4033
47.9 IPS |
|
Face Detection (HP)
|
100% |
37133
441.2 IPS |
|
Face Detection (Q)
|
100% |
47516
564.6 IPS |
|
Depth Estimation (SP)
|
100% |
7295
56.2 IPS |
|
Depth Estimation (HP)
|
99% |
100680
775.7 IPS |
|
Depth Estimation (Q)
|
85% |
115689
904.5 IPS |
|
Style Transfer (SP)
|
100% |
30893
39.7 IPS |
|
Style Transfer (HP)
|
100% |
218970
281.5 IPS |
|
Style Transfer (Q)
|
96% |
213013
274.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5968
220.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
42135
1.56 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49520
1.83 KIPS |
|
Text Classification (SP)
|
100% |
2646
3.53 KIPS |
|
Text Classification (HP)
|
100% |
4569
6.10 KIPS |
|
Text Classification (Q)
|
93% |
4751
6.38 KIPS |
|
Machine Translation (SP)
|
100% |
4826
83.1 IPS |
|
Machine Translation (HP)
|
100% |
4726
81.4 IPS |
|
Machine Translation (Q)
|
98% |
4645
80.3 IPS |