User | everestsky |
Upload Date | May 20 2025 01:22 AM |
Views | 4 |
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% |
2128
395.7 IPS |
|
Image Classification (HP)
|
100% |
3074
571.6 IPS |
|
Image Classification (Q)
|
96% |
2206
412.0 IPS |
|
Image Segmentation (SP)
|
100% |
2540
41.2 IPS |
|
Image Segmentation (HP)
|
100% |
3698
59.9 IPS |
|
Image Segmentation (Q)
|
99% |
4008
65.0 IPS |
|
Pose Estimation (SP)
|
100% |
19218
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
32433
37.8 IPS |
|
Pose Estimation (Q)
|
95% |
24929
29.2 IPS |
|
Object Detection (SP)
|
100% |
2585
205.0 IPS |
|
Object Detection (HP)
|
97% |
3882
309.0 IPS |
|
Object Detection (Q)
|
94% |
2692
214.6 IPS |
|
Face Detection (SP)
|
100% |
4796
57.0 IPS |
|
Face Detection (HP)
|
100% |
8091
96.1 IPS |
|
Face Detection (Q)
|
100% |
4763
56.6 IPS |
|
Depth Estimation (SP)
|
100% |
8869
68.3 IPS |
|
Depth Estimation (HP)
|
97% |
15031
116.2 IPS |
|
Depth Estimation (Q)
|
86% |
10477
81.8 IPS |
|
Style Transfer (SP)
|
100% |
37200
47.8 IPS |
|
Style Transfer (HP)
|
100% |
53960
69.4 IPS |
|
Style Transfer (Q)
|
96% |
40549
52.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
7231
267.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
9647
356.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
5343
197.3 IPS |
|
Text Classification (SP)
|
100% |
2985
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5467
7.30 KIPS |
|
Text Classification (Q)
|
93% |
5379
7.22 KIPS |
|
Machine Translation (SP)
|
100% |
6057
104.3 IPS |
|
Machine Translation (HP)
|
98% |
9062
156.6 IPS |
|
Machine Translation (Q)
|
98% |
9001
155.6 IPS |