User | fp32 |
Upload Date | January 24 2025 04:39 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7877
1.46 KIPS |
|
Image Classification (HP)
|
100% |
8614
1.60 KIPS |
|
Image Classification (Q)
|
97% |
6853
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
11946
193.7 IPS |
|
Image Segmentation (HP)
|
100% |
13062
211.7 IPS |
|
Image Segmentation (Q)
|
99% |
13440
217.9 IPS |
|
Pose Estimation (SP)
|
100% |
56710
66.2 IPS |
|
Pose Estimation (HP)
|
100% |
59199
69.1 IPS |
|
Pose Estimation (Q)
|
95% |
55911
65.5 IPS |
|
Object Detection (SP)
|
100% |
7245
574.6 IPS |
|
Object Detection (HP)
|
100% |
7674
608.7 IPS |
|
Object Detection (Q)
|
91% |
6482
518.0 IPS |
|
Face Detection (SP)
|
100% |
25339
301.1 IPS |
|
Face Detection (HP)
|
100% |
27945
332.0 IPS |
|
Face Detection (Q)
|
100% |
20940
248.8 IPS |
|
Depth Estimation (SP)
|
100% |
33597
258.8 IPS |
|
Depth Estimation (HP)
|
99% |
36278
279.5 IPS |
|
Depth Estimation (Q)
|
85% |
29191
228.1 IPS |
|
Style Transfer (SP)
|
100% |
123394
158.6 IPS |
|
Style Transfer (HP)
|
100% |
134610
173.0 IPS |
|
Style Transfer (Q)
|
96% |
128015
165.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
22805
842.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
24939
920.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
19317
713.3 IPS |
|
Text Classification (SP)
|
100% |
2932
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5280
7.05 KIPS |
|
Text Classification (Q)
|
93% |
5180
6.95 KIPS |
|
Machine Translation (SP)
|
100% |
1473
25.4 IPS |
|
Machine Translation (HP)
|
100% |
1507
26.0 IPS |
|
Machine Translation (Q)
|
98% |
1381
23.9 IPS |