Upload Date | November 19 2024 08:00 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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% |
1497
278.4 IPS |
|
Image Classification (HP)
|
100% |
2411
448.3 IPS |
|
Image Classification (Q)
|
96% |
1821
340.1 IPS |
|
Image Segmentation (SP)
|
100% |
1819
29.5 IPS |
|
Image Segmentation (HP)
|
100% |
2678
43.4 IPS |
|
Image Segmentation (Q)
|
99% |
3368
54.6 IPS |
|
Pose Estimation (SP)
|
100% |
16744
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
28582
33.3 IPS |
|
Pose Estimation (Q)
|
95% |
22457
26.3 IPS |
|
Object Detection (SP)
|
100% |
1974
156.6 IPS |
|
Object Detection (HP)
|
97% |
2919
232.4 IPS |
|
Object Detection (Q)
|
94% |
2182
173.9 IPS |
|
Face Detection (SP)
|
100% |
4093
48.6 IPS |
|
Face Detection (HP)
|
100% |
6808
80.9 IPS |
|
Face Detection (Q)
|
100% |
4043
48.0 IPS |
|
Depth Estimation (SP)
|
100% |
7460
57.5 IPS |
|
Depth Estimation (HP)
|
98% |
13680
105.7 IPS |
|
Depth Estimation (Q)
|
85% |
9514
74.4 IPS |
|
Style Transfer (SP)
|
100% |
31088
40.0 IPS |
|
Style Transfer (HP)
|
100% |
44632
57.4 IPS |
|
Style Transfer (Q)
|
96% |
35029
45.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5745
212.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
7550
278.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
5023
185.5 IPS |
|
Text Classification (SP)
|
100% |
2721
3.63 KIPS |
|
Text Classification (HP)
|
100% |
4954
6.61 KIPS |
|
Text Classification (Q)
|
93% |
4661
6.25 KIPS |
|
Machine Translation (SP)
|
100% |
4736
81.6 IPS |
|
Machine Translation (HP)
|
98% |
7087
122.5 IPS |
|
Machine Translation (Q)
|
98% |
6980
120.6 IPS |