User | BennyDaBall |
Upload Date | February 21 2025 04:44 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2074
385.8 IPS |
|
Image Classification (HP)
|
100% |
17030
3.17 KIPS |
|
Image Classification (Q)
|
97% |
22343
4.17 KIPS |
|
Image Segmentation (SP)
|
100% |
2435
39.5 IPS |
|
Image Segmentation (HP)
|
100% |
23107
374.6 IPS |
|
Image Segmentation (Q)
|
99% |
31949
517.9 IPS |
|
Pose Estimation (SP)
|
100% |
18791
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
123188
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
229210
268.6 IPS |
|
Object Detection (SP)
|
100% |
2477
196.4 IPS |
|
Object Detection (HP)
|
100% |
19443
1.54 KIPS |
|
Object Detection (Q)
|
91% |
23453
1.87 KIPS |
|
Face Detection (SP)
|
100% |
4535
53.9 IPS |
|
Face Detection (HP)
|
100% |
44322
526.6 IPS |
|
Face Detection (Q)
|
100% |
64256
763.5 IPS |
|
Depth Estimation (SP)
|
100% |
8824
68.0 IPS |
|
Depth Estimation (HP)
|
99% |
105102
809.8 IPS |
|
Depth Estimation (Q)
|
85% |
176701
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35278
45.4 IPS |
|
Style Transfer (HP)
|
100% |
237584
305.4 IPS |
|
Style Transfer (Q)
|
96% |
303579
391.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7014
259.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
45531
1.68 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77355
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2912
3.89 KIPS |
|
Text Classification (HP)
|
100% |
5056
6.75 KIPS |
|
Text Classification (Q)
|
93% |
5271
7.07 KIPS |
|
Machine Translation (SP)
|
100% |
5636
97.1 IPS |
|
Machine Translation (HP)
|
100% |
16065
276.7 IPS |
|
Machine Translation (Q)
|
98% |
16093
278.1 IPS |