User | anthonynelzin |
Upload Date | March 13 2025 09:33 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Ultra |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D2082) |
Model | Mac15,14 |
Model ID | Mac15,14 |
Motherboard | Mac15,14 |
CPU Information | |
---|---|
Name | Apple M3 Ultra |
Topology | 1 Processor, 28 Cores |
Identifier | Apple M3 Ultra |
Base Frequency | 3.51 GHz |
Cluster 1 | 20 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1691
314.5 IPS |
|
Image Classification (HP)
|
100% |
15230
2.83 KIPS |
|
Image Classification (Q)
|
97% |
16777
3.13 KIPS |
|
Image Segmentation (SP)
|
100% |
2068
33.5 IPS |
|
Image Segmentation (HP)
|
100% |
20972
340.0 IPS |
|
Image Segmentation (Q)
|
99% |
26708
432.9 IPS |
|
Pose Estimation (SP)
|
100% |
19905
23.2 IPS |
|
Pose Estimation (HP)
|
100% |
120593
140.7 IPS |
|
Pose Estimation (Q)
|
95% |
119258
139.8 IPS |
|
Object Detection (SP)
|
100% |
2159
171.3 IPS |
|
Object Detection (HP)
|
100% |
17562
1.39 KIPS |
|
Object Detection (Q)
|
91% |
18428
1.47 KIPS |
|
Face Detection (SP)
|
100% |
4620
54.9 IPS |
|
Face Detection (HP)
|
100% |
37376
444.1 IPS |
|
Face Detection (Q)
|
100% |
47060
559.2 IPS |
|
Depth Estimation (SP)
|
100% |
8013
61.7 IPS |
|
Depth Estimation (HP)
|
99% |
102926
793.0 IPS |
|
Depth Estimation (Q)
|
85% |
117379
917.7 IPS |
|
Style Transfer (SP)
|
100% |
32512
41.8 IPS |
|
Style Transfer (HP)
|
100% |
217617
279.7 IPS |
|
Style Transfer (Q)
|
96% |
213205
275.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
6917
255.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
37711
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49097
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2655
3.54 KIPS |
|
Text Classification (HP)
|
100% |
4823
6.44 KIPS |
|
Text Classification (Q)
|
93% |
4814
6.46 KIPS |
|
Machine Translation (SP)
|
100% |
5525
95.2 IPS |
|
Machine Translation (HP)
|
100% |
4607
79.4 IPS |
|
Machine Translation (Q)
|
98% |
4861
84.0 IPS |