Upload Date | December 25 2024 06:08 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,6 |
Motherboard | Mac16,6 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 3.60 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2022
376.1 IPS |
|
Image Classification (HP)
|
100% |
2883
536.1 IPS |
|
Image Classification (Q)
|
96% |
1935
361.3 IPS |
|
Image Segmentation (SP)
|
100% |
2221
36.0 IPS |
|
Image Segmentation (HP)
|
100% |
3170
51.4 IPS |
|
Image Segmentation (Q)
|
99% |
3445
55.8 IPS |
|
Pose Estimation (SP)
|
100% |
16236
18.9 IPS |
|
Pose Estimation (HP)
|
100% |
28694
33.5 IPS |
|
Pose Estimation (Q)
|
95% |
22607
26.5 IPS |
|
Object Detection (SP)
|
100% |
2404
190.7 IPS |
|
Object Detection (HP)
|
97% |
3578
284.8 IPS |
|
Object Detection (Q)
|
94% |
2473
197.1 IPS |
|
Face Detection (SP)
|
100% |
4265
50.7 IPS |
|
Face Detection (HP)
|
100% |
7214
85.7 IPS |
|
Face Detection (Q)
|
100% |
4033
47.9 IPS |
|
Depth Estimation (SP)
|
100% |
8002
61.7 IPS |
|
Depth Estimation (HP)
|
97% |
13685
105.8 IPS |
|
Depth Estimation (Q)
|
86% |
9594
74.9 IPS |
|
Style Transfer (SP)
|
100% |
32795
42.2 IPS |
|
Style Transfer (HP)
|
100% |
47027
60.5 IPS |
|
Style Transfer (Q)
|
96% |
35920
46.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
6636
245.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
8946
330.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
4951
182.8 IPS |
|
Text Classification (SP)
|
100% |
2856
3.81 KIPS |
|
Text Classification (HP)
|
100% |
5042
6.73 KIPS |
|
Text Classification (Q)
|
93% |
4982
6.69 KIPS |
|
Machine Translation (SP)
|
100% |
5608
96.6 IPS |
|
Machine Translation (HP)
|
98% |
8422
145.5 IPS |
|
Machine Translation (Q)
|
98% |
8456
146.1 IPS |