User | Phizzle |
Upload Date | December 15 2024 07:22 PM |
Views | 11 |
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 | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2083
387.5 IPS |
|
Image Classification (HP)
|
100% |
17836
3.32 KIPS |
|
Image Classification (Q)
|
97% |
21972
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2507
40.6 IPS |
|
Image Segmentation (HP)
|
100% |
23289
377.5 IPS |
|
Image Segmentation (Q)
|
99% |
32224
522.4 IPS |
|
Pose Estimation (SP)
|
100% |
18891
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123437
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
229750
269.3 IPS |
|
Object Detection (SP)
|
100% |
2502
198.5 IPS |
|
Object Detection (HP)
|
100% |
20084
1.59 KIPS |
|
Object Detection (Q)
|
91% |
23730
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4523
53.7 IPS |
|
Face Detection (HP)
|
100% |
44541
529.2 IPS |
|
Face Detection (Q)
|
100% |
55692
661.7 IPS |
|
Depth Estimation (SP)
|
100% |
8774
67.6 IPS |
|
Depth Estimation (HP)
|
99% |
107240
826.2 IPS |
|
Depth Estimation (Q)
|
85% |
179141
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
35484
45.6 IPS |
|
Style Transfer (HP)
|
100% |
237240
305.0 IPS |
|
Style Transfer (Q)
|
96% |
303689
391.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
7029
259.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
46867
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78618
2.90 KIPS |
|
Text Classification (SP)
|
100% |
2922
3.90 KIPS |
|
Text Classification (HP)
|
100% |
5259
7.02 KIPS |
|
Text Classification (Q)
|
93% |
5137
6.89 KIPS |
|
Machine Translation (SP)
|
100% |
5827
100.4 IPS |
|
Machine Translation (HP)
|
100% |
16565
285.3 IPS |
|
Machine Translation (Q)
|
98% |
16647
287.7 IPS |