User | pers1 |
Upload Date | November 01 2024 05:42 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1537
285.8 IPS |
|
Image Classification (HP)
|
100% |
16579
3.08 KIPS |
|
Image Classification (Q)
|
97% |
18089
3.38 KIPS |
|
Image Segmentation (SP)
|
100% |
1945
31.5 IPS |
|
Image Segmentation (HP)
|
100% |
21779
353.0 IPS |
|
Image Segmentation (Q)
|
99% |
27205
441.0 IPS |
|
Pose Estimation (SP)
|
100% |
16778
19.6 IPS |
|
Pose Estimation (HP)
|
100% |
120572
140.7 IPS |
|
Pose Estimation (Q)
|
95% |
118934
139.4 IPS |
|
Object Detection (SP)
|
100% |
2009
159.4 IPS |
|
Object Detection (HP)
|
100% |
16916
1.34 KIPS |
|
Object Detection (Q)
|
91% |
18748
1.50 KIPS |
|
Face Detection (SP)
|
100% |
4096
48.7 IPS |
|
Face Detection (HP)
|
100% |
38804
461.1 IPS |
|
Face Detection (Q)
|
100% |
49731
590.9 IPS |
|
Depth Estimation (SP)
|
100% |
7371
56.8 IPS |
|
Depth Estimation (HP)
|
99% |
103463
797.1 IPS |
|
Depth Estimation (Q)
|
85% |
115940
906.5 IPS |
|
Style Transfer (SP)
|
100% |
30878
39.7 IPS |
|
Style Transfer (HP)
|
100% |
222790
286.4 IPS |
|
Style Transfer (Q)
|
96% |
209213
270.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5983
220.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
38606
1.43 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52249
1.93 KIPS |
|
Text Classification (SP)
|
100% |
2790
3.72 KIPS |
|
Text Classification (HP)
|
100% |
4937
6.59 KIPS |
|
Text Classification (Q)
|
93% |
4908
6.59 KIPS |
|
Machine Translation (SP)
|
100% |
5049
87.0 IPS |
|
Machine Translation (HP)
|
100% |
7692
132.5 IPS |
|
Machine Translation (Q)
|
98% |
8146
140.8 IPS |