User | everestsky |
Upload Date | May 20 2025 01:33 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D2059) |
Model | Mac16,9 |
Model ID | Mac16,9 |
Motherboard | Mac16,9 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2129
395.9 IPS |
|
Image Classification (HP)
|
100% |
3082
573.1 IPS |
|
Image Classification (Q)
|
96% |
2208
412.4 IPS |
|
Image Segmentation (SP)
|
100% |
2551
41.4 IPS |
|
Image Segmentation (HP)
|
100% |
3631
58.9 IPS |
|
Image Segmentation (Q)
|
99% |
3992
64.7 IPS |
|
Pose Estimation (SP)
|
100% |
19157
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
32406
37.8 IPS |
|
Pose Estimation (Q)
|
95% |
25022
29.3 IPS |
|
Object Detection (SP)
|
100% |
2578
204.5 IPS |
|
Object Detection (HP)
|
97% |
3897
310.2 IPS |
|
Object Detection (Q)
|
94% |
2704
215.5 IPS |
|
Face Detection (SP)
|
100% |
4789
56.9 IPS |
|
Face Detection (HP)
|
100% |
8221
97.7 IPS |
|
Face Detection (Q)
|
100% |
4769
56.7 IPS |
|
Depth Estimation (SP)
|
100% |
9066
69.8 IPS |
|
Depth Estimation (HP)
|
97% |
15099
116.7 IPS |
|
Depth Estimation (Q)
|
86% |
10349
80.8 IPS |
|
Style Transfer (SP)
|
100% |
37370
48.0 IPS |
|
Style Transfer (HP)
|
100% |
54022
69.4 IPS |
|
Style Transfer (Q)
|
96% |
40256
52.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7201
265.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
9608
354.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
5340
197.2 IPS |
|
Text Classification (SP)
|
100% |
2969
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5307
7.08 KIPS |
|
Text Classification (Q)
|
93% |
5278
7.08 KIPS |
|
Machine Translation (SP)
|
100% |
6029
103.9 IPS |
|
Machine Translation (HP)
|
98% |
9078
156.9 IPS |
|
Machine Translation (Q)
|
98% |
8950
154.7 IPS |