User | TheWojtek |
Upload Date | February 14 2025 01:00 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 4.46 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7018
1.31 KIPS |
|
Image Classification (HP)
|
100% |
7420
1.38 KIPS |
|
Image Classification (Q)
|
97% |
6302
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
10718
173.7 IPS |
|
Image Segmentation (HP)
|
100% |
11371
184.3 IPS |
|
Image Segmentation (Q)
|
99% |
11431
185.3 IPS |
|
Pose Estimation (SP)
|
100% |
46142
53.8 IPS |
|
Pose Estimation (HP)
|
100% |
48395
56.5 IPS |
|
Pose Estimation (Q)
|
95% |
45843
53.7 IPS |
|
Object Detection (SP)
|
100% |
6928
549.5 IPS |
|
Object Detection (HP)
|
100% |
7254
575.4 IPS |
|
Object Detection (Q)
|
91% |
6070
485.1 IPS |
|
Face Detection (SP)
|
100% |
23026
273.6 IPS |
|
Face Detection (HP)
|
100% |
24994
297.0 IPS |
|
Face Detection (Q)
|
100% |
18245
216.8 IPS |
|
Depth Estimation (SP)
|
100% |
31029
239.1 IPS |
|
Depth Estimation (HP)
|
99% |
32989
254.2 IPS |
|
Depth Estimation (Q)
|
85% |
28912
226.0 IPS |
|
Style Transfer (SP)
|
100% |
105705
135.9 IPS |
|
Style Transfer (HP)
|
100% |
113775
146.3 IPS |
|
Style Transfer (Q)
|
96% |
108280
139.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
16878
623.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
17722
654.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
15054
555.9 IPS |
|
Text Classification (SP)
|
100% |
2947
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5120
6.83 KIPS |
|
Text Classification (Q)
|
93% |
5146
6.91 KIPS |
|
Machine Translation (SP)
|
100% |
970
16.7 IPS |
|
Machine Translation (HP)
|
100% |
875
15.1 IPS |
|
Machine Translation (Q)
|
98% |
1019
17.6 IPS |