User | N-L |
Upload Date | December 28 2024 01:55 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2080
386.9 IPS |
|
Image Classification (HP)
|
100% |
17990
3.35 KIPS |
|
Image Classification (Q)
|
97% |
22861
4.27 KIPS |
|
Image Segmentation (SP)
|
100% |
2529
41.0 IPS |
|
Image Segmentation (HP)
|
100% |
23226
376.5 IPS |
|
Image Segmentation (Q)
|
99% |
31969
518.2 IPS |
|
Pose Estimation (SP)
|
100% |
18821
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123273
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
231281
271.1 IPS |
|
Object Detection (SP)
|
100% |
2467
195.7 IPS |
|
Object Detection (HP)
|
100% |
19895
1.58 KIPS |
|
Object Detection (Q)
|
91% |
24726
1.98 KIPS |
|
Face Detection (SP)
|
100% |
4498
53.4 IPS |
|
Face Detection (HP)
|
100% |
44391
527.5 IPS |
|
Face Detection (Q)
|
100% |
60667
720.9 IPS |
|
Depth Estimation (SP)
|
100% |
8702
67.0 IPS |
|
Depth Estimation (HP)
|
99% |
105733
814.6 IPS |
|
Depth Estimation (Q)
|
85% |
181091
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
35181
45.2 IPS |
|
Style Transfer (HP)
|
100% |
237716
305.6 IPS |
|
Style Transfer (Q)
|
96% |
301236
388.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7017
259.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
47365
1.75 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79671
2.94 KIPS |
|
Text Classification (SP)
|
100% |
2931
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5549
7.41 KIPS |
|
Text Classification (Q)
|
93% |
5076
6.81 KIPS |
|
Machine Translation (SP)
|
100% |
5642
97.2 IPS |
|
Machine Translation (HP)
|
100% |
16596
285.9 IPS |
|
Machine Translation (Q)
|
98% |
16659
287.9 IPS |