Upload Date | December 13 2024 11:49 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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% |
7323
1.36 KIPS |
|
Image Classification (HP)
|
100% |
7516
1.40 KIPS |
|
Image Classification (Q)
|
99% |
7555
1.41 KIPS |
|
Image Segmentation (SP)
|
100% |
13645
221.2 IPS |
|
Image Segmentation (HP)
|
100% |
14468
234.5 IPS |
|
Image Segmentation (Q)
|
100% |
14461
234.4 IPS |
|
Pose Estimation (SP)
|
100% |
66739
77.9 IPS |
|
Pose Estimation (HP)
|
100% |
69481
81.1 IPS |
|
Pose Estimation (Q)
|
97% |
63080
73.9 IPS |
|
Object Detection (SP)
|
100% |
7330
581.4 IPS |
|
Object Detection (HP)
|
100% |
7732
613.3 IPS |
|
Object Detection (Q)
|
91% |
6593
526.8 IPS |
|
Face Detection (SP)
|
100% |
26854
319.1 IPS |
|
Face Detection (HP)
|
100% |
30504
362.5 IPS |
|
Face Detection (Q)
|
100% |
22947
272.7 IPS |
|
Depth Estimation (SP)
|
100% |
32712
252.0 IPS |
|
Depth Estimation (HP)
|
99% |
34541
266.1 IPS |
|
Depth Estimation (Q)
|
97% |
5815
45.0 IPS |
|
Style Transfer (SP)
|
100% |
144059
185.2 IPS |
|
Style Transfer (HP)
|
100% |
160688
206.6 IPS |
|
Style Transfer (Q)
|
100% |
160666
206.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
21451
792.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
22841
843.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
17611
652.5 IPS |
|
Text Classification (SP)
|
100% |
2698
3.60 KIPS |
|
Text Classification (HP)
|
100% |
4711
6.29 KIPS |
|
Text Classification (Q)
|
93% |
4670
6.27 KIPS |
|
Machine Translation (SP)
|
100% |
2151
37.0 IPS |
|
Machine Translation (HP)
|
98% |
6889
119.0 IPS |
|
Machine Translation (Q)
|
98% |
6906
119.3 IPS |