User | MegumiKatou |
Upload Date | May 20 2025 02:53 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1507
280.3 IPS |
|
Image Classification (HP)
|
100% |
16574
3.08 KIPS |
|
Image Classification (Q)
|
97% |
18018
3.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1799
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
21676
351.4 IPS |
|
Image Segmentation (Q)
|
99% |
27396
444.1 IPS |
|
Pose Estimation (SP)
|
100% |
16633
19.4 IPS |
|
Pose Estimation (HP)
|
100% |
119488
139.4 IPS |
|
Pose Estimation (Q)
|
95% |
118839
139.3 IPS |
|
Object Detection (SP)
|
100% |
1942
154.0 IPS |
|
Object Detection (HP)
|
100% |
16876
1.34 KIPS |
|
Object Detection (Q)
|
91% |
16657
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3968
47.2 IPS |
|
Face Detection (HP)
|
100% |
37930
450.7 IPS |
|
Face Detection (Q)
|
100% |
49327
586.1 IPS |
|
Depth Estimation (SP)
|
100% |
7144
55.0 IPS |
|
Depth Estimation (HP)
|
99% |
101214
779.8 IPS |
|
Depth Estimation (Q)
|
85% |
119704
935.9 IPS |
|
Style Transfer (SP)
|
100% |
30347
39.0 IPS |
|
Style Transfer (HP)
|
100% |
219232
281.8 IPS |
|
Style Transfer (Q)
|
96% |
208832
269.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5767
213.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
39129
1.44 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52564
1.94 KIPS |
|
Text Classification (SP)
|
100% |
2798
3.73 KIPS |
|
Text Classification (HP)
|
100% |
5115
6.83 KIPS |
|
Text Classification (Q)
|
93% |
4996
6.70 KIPS |
|
Machine Translation (SP)
|
100% |
4760
82.0 IPS |
|
Machine Translation (HP)
|
100% |
4999
86.1 IPS |
|
Machine Translation (Q)
|
98% |
5428
93.8 IPS |