User | ndelettre |
Upload Date | December 13 2024 06:06 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
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% |
2079
386.6 IPS |
|
Image Classification (HP)
|
100% |
17721
3.30 KIPS |
|
Image Classification (Q)
|
97% |
22239
4.15 KIPS |
|
Image Segmentation (SP)
|
100% |
2527
41.0 IPS |
|
Image Segmentation (HP)
|
100% |
23203
376.1 IPS |
|
Image Segmentation (Q)
|
99% |
32101
520.4 IPS |
|
Pose Estimation (SP)
|
100% |
18946
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123483
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
231357
271.2 IPS |
|
Object Detection (SP)
|
100% |
2485
197.1 IPS |
|
Object Detection (HP)
|
100% |
20186
1.60 KIPS |
|
Object Detection (Q)
|
91% |
24744
1.98 KIPS |
|
Face Detection (SP)
|
100% |
4544
54.0 IPS |
|
Face Detection (HP)
|
100% |
44458
528.3 IPS |
|
Face Detection (Q)
|
100% |
64883
771.0 IPS |
|
Depth Estimation (SP)
|
100% |
8855
68.2 IPS |
|
Depth Estimation (HP)
|
99% |
111704
860.6 IPS |
|
Depth Estimation (Q)
|
85% |
177401
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35072
45.1 IPS |
|
Style Transfer (HP)
|
100% |
238396
306.5 IPS |
|
Style Transfer (Q)
|
96% |
302238
390.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7060
260.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
45911
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77894
2.88 KIPS |
|
Text Classification (SP)
|
100% |
2931
3.91 KIPS |
|
Text Classification (HP)
|
100% |
4894
6.53 KIPS |
|
Text Classification (Q)
|
93% |
4903
6.58 KIPS |
|
Machine Translation (SP)
|
100% |
5802
99.9 IPS |
|
Machine Translation (HP)
|
100% |
16190
278.9 IPS |
|
Machine Translation (Q)
|
98% |
16182
279.6 IPS |