Upload Date | August 16 2024 01:45 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
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% |
1711
318.2 IPS |
|
Image Classification (HP)
|
100% |
2049
381.1 IPS |
|
Image Classification (Q)
|
99% |
2027
378.1 IPS |
|
Image Segmentation (SP)
|
100% |
1485
24.1 IPS |
|
Image Segmentation (HP)
|
100% |
1414
22.9 IPS |
|
Image Segmentation (Q)
|
100% |
1415
22.9 IPS |
|
Pose Estimation (SP)
|
100% |
8629
10.1 IPS |
|
Pose Estimation (HP)
|
100% |
17046
19.9 IPS |
|
Pose Estimation (Q)
|
96% |
14583
17.1 IPS |
|
Object Detection (SP)
|
100% |
1852
146.9 IPS |
|
Object Detection (HP)
|
97% |
2565
204.2 IPS |
|
Object Detection (Q)
|
94% |
1953
155.7 IPS |
|
Face Detection (SP)
|
100% |
3468
41.2 IPS |
|
Face Detection (HP)
|
100% |
5053
60.0 IPS |
|
Face Detection (Q)
|
100% |
3325
39.5 IPS |
|
Depth Estimation (SP)
|
100% |
6762
52.1 IPS |
|
Depth Estimation (HP)
|
99% |
9731
75.2 IPS |
|
Depth Estimation (Q)
|
96% |
4107
31.8 IPS |
|
Style Transfer (SP)
|
100% |
19839
25.5 IPS |
|
Style Transfer (HP)
|
100% |
29689
38.2 IPS |
|
Style Transfer (Q)
|
100% |
29634
38.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4969
183.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
5540
204.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
4200
155.6 IPS |
|
Text Classification (SP)
|
100% |
2739
3.66 KIPS |
|
Text Classification (HP)
|
100% |
4598
6.14 KIPS |
|
Text Classification (Q)
|
93% |
4746
6.37 KIPS |
|
Machine Translation (SP)
|
100% |
3020
52.0 IPS |
|
Machine Translation (HP)
|
98% |
4745
82.0 IPS |
|
Machine Translation (Q)
|
98% |
4696
81.2 IPS |