User | tebruno99 |
Upload Date | March 27 2025 11:34 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2079
386.7 IPS |
|
Image Classification (HP)
|
100% |
17394
3.23 KIPS |
|
Image Classification (Q)
|
97% |
23744
4.43 KIPS |
|
Image Segmentation (SP)
|
100% |
2513
40.7 IPS |
|
Image Segmentation (HP)
|
100% |
23199
376.1 IPS |
|
Image Segmentation (Q)
|
99% |
32277
523.2 IPS |
|
Pose Estimation (SP)
|
100% |
18837
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123112
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
231236
271.0 IPS |
|
Object Detection (SP)
|
100% |
2472
196.0 IPS |
|
Object Detection (HP)
|
100% |
20089
1.59 KIPS |
|
Object Detection (Q)
|
91% |
24128
1.93 KIPS |
|
Face Detection (SP)
|
100% |
4487
53.3 IPS |
|
Face Detection (HP)
|
100% |
44981
534.5 IPS |
|
Face Detection (Q)
|
100% |
58303
692.8 IPS |
|
Depth Estimation (SP)
|
100% |
8788
67.7 IPS |
|
Depth Estimation (HP)
|
99% |
112418
866.1 IPS |
|
Depth Estimation (Q)
|
85% |
180149
1.41 KIPS |
|
Style Transfer (SP)
|
100% |
35743
45.9 IPS |
|
Style Transfer (HP)
|
100% |
238585
306.7 IPS |
|
Style Transfer (Q)
|
96% |
300068
387.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7040
260.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
46659
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79620
2.94 KIPS |
|
Text Classification (SP)
|
100% |
2941
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5127
6.84 KIPS |
|
Text Classification (Q)
|
93% |
5196
6.97 KIPS |
|
Machine Translation (SP)
|
100% |
5758
99.2 IPS |
|
Machine Translation (HP)
|
100% |
16874
290.7 IPS |
|
Machine Translation (Q)
|
98% |
16906
292.2 IPS |