User | iGeneration |
Upload Date | January 23 2025 08:50 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.33 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2076
386.0 IPS |
|
Image Classification (HP)
|
100% |
18313
3.41 KIPS |
|
Image Classification (Q)
|
97% |
22756
4.25 KIPS |
|
Image Segmentation (SP)
|
100% |
2575
41.7 IPS |
|
Image Segmentation (HP)
|
100% |
23726
384.6 IPS |
|
Image Segmentation (Q)
|
99% |
33165
537.6 IPS |
|
Pose Estimation (SP)
|
100% |
18932
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123918
144.6 IPS |
|
Pose Estimation (Q)
|
95% |
217101
254.5 IPS |
|
Object Detection (SP)
|
100% |
2532
200.9 IPS |
|
Object Detection (HP)
|
100% |
20410
1.62 KIPS |
|
Object Detection (Q)
|
91% |
27260
2.18 KIPS |
|
Face Detection (SP)
|
100% |
4307
51.2 IPS |
|
Face Detection (HP)
|
100% |
45449
540.0 IPS |
|
Face Detection (Q)
|
100% |
59961
712.5 IPS |
|
Depth Estimation (SP)
|
100% |
8606
66.3 IPS |
|
Depth Estimation (HP)
|
99% |
108315
834.5 IPS |
|
Depth Estimation (Q)
|
85% |
181198
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
34362
44.2 IPS |
|
Style Transfer (HP)
|
100% |
240676
309.4 IPS |
|
Style Transfer (Q)
|
96% |
308726
398.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
7180
265.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
48392
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83653
3.09 KIPS |
|
Text Classification (SP)
|
100% |
2952
3.94 KIPS |
|
Text Classification (HP)
|
100% |
5621
7.50 KIPS |
|
Text Classification (Q)
|
93% |
5516
7.40 KIPS |
|
Machine Translation (SP)
|
100% |
5456
94.0 IPS |
|
Machine Translation (HP)
|
100% |
16802
289.4 IPS |
|
Machine Translation (Q)
|
98% |
17729
306.4 IPS |