User | Simondeminuit |
Upload Date | January 17 2025 12:01 AM |
Views | 20 |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2088
388.3 IPS |
|
Image Classification (HP)
|
100% |
17867
3.32 KIPS |
|
Image Classification (Q)
|
97% |
22981
4.29 KIPS |
|
Image Segmentation (SP)
|
100% |
2510
40.7 IPS |
|
Image Segmentation (HP)
|
100% |
23254
377.0 IPS |
|
Image Segmentation (Q)
|
99% |
32561
527.8 IPS |
|
Pose Estimation (SP)
|
100% |
18823
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123573
144.2 IPS |
|
Pose Estimation (Q)
|
95% |
232083
272.0 IPS |
|
Object Detection (SP)
|
100% |
2492
197.7 IPS |
|
Object Detection (HP)
|
100% |
20096
1.59 KIPS |
|
Object Detection (Q)
|
91% |
24708
1.97 KIPS |
|
Face Detection (SP)
|
100% |
4589
54.5 IPS |
|
Face Detection (HP)
|
100% |
44699
531.1 IPS |
|
Face Detection (Q)
|
100% |
62344
740.8 IPS |
|
Depth Estimation (SP)
|
100% |
8857
68.2 IPS |
|
Depth Estimation (HP)
|
99% |
115179
887.4 IPS |
|
Depth Estimation (Q)
|
85% |
184407
1.44 KIPS |
|
Style Transfer (SP)
|
100% |
35095
45.1 IPS |
|
Style Transfer (HP)
|
100% |
239228
307.5 IPS |
|
Style Transfer (Q)
|
96% |
304672
393.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7082
261.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
47035
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80594
2.98 KIPS |
|
Text Classification (SP)
|
100% |
2954
3.94 KIPS |
|
Text Classification (HP)
|
100% |
5516
7.36 KIPS |
|
Text Classification (Q)
|
93% |
5677
7.62 KIPS |
|
Machine Translation (SP)
|
100% |
5916
101.9 IPS |
|
Machine Translation (HP)
|
100% |
17225
296.7 IPS |
|
Machine Translation (Q)
|
98% |
17387
300.5 IPS |