Upload Date | November 17 2024 09:33 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2082) |
Model | Mac16,8 |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6825
1.27 KIPS |
|
Image Classification (HP)
|
100% |
7372
1.37 KIPS |
|
Image Classification (Q)
|
97% |
6228
1.16 KIPS |
|
Image Segmentation (SP)
|
100% |
10502
170.2 IPS |
|
Image Segmentation (HP)
|
100% |
11139
180.6 IPS |
|
Image Segmentation (Q)
|
99% |
11414
185.0 IPS |
|
Pose Estimation (SP)
|
100% |
46152
53.9 IPS |
|
Pose Estimation (HP)
|
100% |
48170
56.2 IPS |
|
Pose Estimation (Q)
|
95% |
45641
53.5 IPS |
|
Object Detection (SP)
|
100% |
6733
534.1 IPS |
|
Object Detection (HP)
|
100% |
7209
571.9 IPS |
|
Object Detection (Q)
|
91% |
5948
475.3 IPS |
|
Face Detection (SP)
|
100% |
23359
277.6 IPS |
|
Face Detection (HP)
|
100% |
24905
295.9 IPS |
|
Face Detection (Q)
|
100% |
18534
220.2 IPS |
|
Depth Estimation (SP)
|
100% |
30741
236.8 IPS |
|
Depth Estimation (HP)
|
99% |
33028
254.5 IPS |
|
Depth Estimation (Q)
|
85% |
26887
210.1 IPS |
|
Style Transfer (SP)
|
100% |
104411
134.2 IPS |
|
Style Transfer (HP)
|
100% |
112894
145.1 IPS |
|
Style Transfer (Q)
|
96% |
107024
138.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
16687
616.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
17613
650.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
14115
521.2 IPS |
|
Text Classification (SP)
|
100% |
2930
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5163
6.89 KIPS |
|
Text Classification (Q)
|
93% |
5116
6.87 KIPS |
|
Machine Translation (SP)
|
100% |
1987
34.2 IPS |
|
Machine Translation (HP)
|
100% |
2751
47.4 IPS |
|
Machine Translation (Q)
|
98% |
2512
43.4 IPS |