User | anthonynelzin |
Upload Date | March 12 2025 02:18 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D2082) |
Model | Mac16,13 |
Model ID | Mac16,13 |
Motherboard | Mac16,13 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4471
831.5 IPS |
|
Image Classification (HP)
|
100% |
4751
883.5 IPS |
|
Image Classification (Q)
|
97% |
4099
764.9 IPS |
|
Image Segmentation (SP)
|
100% |
4814
78.0 IPS |
|
Image Segmentation (HP)
|
100% |
6682
108.3 IPS |
|
Image Segmentation (Q)
|
99% |
7109
115.2 IPS |
|
Pose Estimation (SP)
|
100% |
28182
32.9 IPS |
|
Pose Estimation (HP)
|
100% |
30042
35.1 IPS |
|
Pose Estimation (Q)
|
95% |
28604
33.5 IPS |
|
Object Detection (SP)
|
100% |
4751
376.9 IPS |
|
Object Detection (HP)
|
100% |
5251
416.5 IPS |
|
Object Detection (Q)
|
91% |
4425
353.6 IPS |
|
Face Detection (SP)
|
100% |
12647
150.3 IPS |
|
Face Detection (HP)
|
100% |
15823
188.0 IPS |
|
Face Detection (Q)
|
100% |
11836
140.6 IPS |
|
Depth Estimation (SP)
|
100% |
20238
155.9 IPS |
|
Depth Estimation (HP)
|
99% |
22270
171.6 IPS |
|
Depth Estimation (Q)
|
85% |
19096
149.3 IPS |
|
Style Transfer (SP)
|
100% |
55163
70.9 IPS |
|
Style Transfer (HP)
|
100% |
67725
87.1 IPS |
|
Style Transfer (Q)
|
96% |
63537
82.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
11551
426.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
12610
465.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
10211
377.0 IPS |
|
Text Classification (SP)
|
100% |
3070
4.10 KIPS |
|
Text Classification (HP)
|
100% |
5620
7.50 KIPS |
|
Text Classification (Q)
|
93% |
5441
7.30 KIPS |
|
Machine Translation (SP)
|
100% |
1188
20.5 IPS |
|
Machine Translation (HP)
|
100% |
693
11.9 IPS |
|
Machine Translation (Q)
|
98% |
891
15.4 IPS |