Upload Date | November 17 2024 11:32 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,10 |
Motherboard | Mac15,10 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1517
282.0 IPS |
|
Image Classification (HP)
|
100% |
16859
3.14 KIPS |
|
Image Classification (Q)
|
97% |
18097
3.38 KIPS |
|
Image Segmentation (SP)
|
100% |
1841
29.8 IPS |
|
Image Segmentation (HP)
|
100% |
21377
346.5 IPS |
|
Image Segmentation (Q)
|
99% |
27550
446.6 IPS |
|
Pose Estimation (SP)
|
100% |
16698
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
120851
141.0 IPS |
|
Pose Estimation (Q)
|
95% |
119066
139.6 IPS |
|
Object Detection (SP)
|
100% |
1967
156.0 IPS |
|
Object Detection (HP)
|
100% |
16796
1.33 KIPS |
|
Object Detection (Q)
|
91% |
17341
1.39 KIPS |
|
Face Detection (SP)
|
100% |
3947
46.9 IPS |
|
Face Detection (HP)
|
100% |
38559
458.2 IPS |
|
Face Detection (Q)
|
100% |
47686
566.6 IPS |
|
Depth Estimation (SP)
|
100% |
7409
57.1 IPS |
|
Depth Estimation (HP)
|
99% |
102896
792.8 IPS |
|
Depth Estimation (Q)
|
85% |
116519
911.0 IPS |
|
Style Transfer (SP)
|
100% |
30554
39.3 IPS |
|
Style Transfer (HP)
|
100% |
220024
282.8 IPS |
|
Style Transfer (Q)
|
96% |
210549
271.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5866
216.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
38025
1.40 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52860
1.95 KIPS |
|
Text Classification (SP)
|
100% |
2903
3.87 KIPS |
|
Text Classification (HP)
|
100% |
5048
6.74 KIPS |
|
Text Classification (Q)
|
93% |
4887
6.56 KIPS |
|
Machine Translation (SP)
|
100% |
1852
31.9 IPS |
|
Machine Translation (HP)
|
98% |
6980
120.6 IPS |
|
Machine Translation (Q)
|
98% |
7105
122.8 IPS |