User | tensojka |
Upload Date | January 28 2025 08:33 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
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% |
2071
385.2 IPS |
|
Image Classification (HP)
|
100% |
17768
3.30 KIPS |
|
Image Classification (Q)
|
97% |
22768
4.25 KIPS |
|
Image Segmentation (SP)
|
100% |
2443
39.6 IPS |
|
Image Segmentation (HP)
|
100% |
23773
385.4 IPS |
|
Image Segmentation (Q)
|
99% |
32739
530.7 IPS |
|
Pose Estimation (SP)
|
100% |
18836
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123447
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
231759
271.6 IPS |
|
Object Detection (SP)
|
100% |
2467
195.7 IPS |
|
Object Detection (HP)
|
100% |
20112
1.60 KIPS |
|
Object Detection (Q)
|
91% |
24481
1.96 KIPS |
|
Face Detection (SP)
|
100% |
4437
52.7 IPS |
|
Face Detection (HP)
|
100% |
43805
520.5 IPS |
|
Face Detection (Q)
|
100% |
63741
757.4 IPS |
|
Depth Estimation (SP)
|
100% |
8615
66.4 IPS |
|
Depth Estimation (HP)
|
99% |
111782
861.2 IPS |
|
Depth Estimation (Q)
|
85% |
177701
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35243
45.3 IPS |
|
Style Transfer (HP)
|
100% |
237932
305.9 IPS |
|
Style Transfer (Q)
|
96% |
305121
393.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6958
256.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46597
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79640
2.94 KIPS |
|
Text Classification (SP)
|
100% |
2917
3.89 KIPS |
|
Text Classification (HP)
|
100% |
6060
8.09 KIPS |
|
Text Classification (Q)
|
93% |
6051
8.12 KIPS |
|
Machine Translation (SP)
|
100% |
5519
95.1 IPS |
|
Machine Translation (HP)
|
100% |
16268
280.2 IPS |
|
Machine Translation (Q)
|
98% |
15298
264.4 IPS |