User | anthonynelzin |
Upload Date | March 13 2025 09:36 AM |
Views | 5 |
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 | 4.05 GHz |
Cluster 1 | 20 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1711
318.2 IPS |
|
Image Classification (HP)
|
100% |
15105
2.81 KIPS |
|
Image Classification (Q)
|
97% |
16766
3.13 KIPS |
|
Image Segmentation (SP)
|
100% |
2133
34.6 IPS |
|
Image Segmentation (HP)
|
100% |
21883
354.7 IPS |
|
Image Segmentation (Q)
|
99% |
27153
440.2 IPS |
|
Pose Estimation (SP)
|
100% |
21548
25.1 IPS |
|
Pose Estimation (HP)
|
100% |
120514
140.6 IPS |
|
Pose Estimation (Q)
|
95% |
119097
139.6 IPS |
|
Object Detection (SP)
|
100% |
2205
174.9 IPS |
|
Object Detection (HP)
|
100% |
18006
1.43 KIPS |
|
Object Detection (Q)
|
91% |
18677
1.49 KIPS |
|
Face Detection (SP)
|
100% |
4692
55.8 IPS |
|
Face Detection (HP)
|
100% |
37902
450.4 IPS |
|
Face Detection (Q)
|
100% |
48761
579.4 IPS |
|
Depth Estimation (SP)
|
100% |
8191
63.1 IPS |
|
Depth Estimation (HP)
|
99% |
101992
785.8 IPS |
|
Depth Estimation (Q)
|
85% |
116614
911.7 IPS |
|
Style Transfer (SP)
|
100% |
34297
44.1 IPS |
|
Style Transfer (HP)
|
100% |
218951
281.5 IPS |
|
Style Transfer (Q)
|
96% |
211482
272.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
7026
259.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
37701
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49528
1.83 KIPS |
|
Text Classification (SP)
|
100% |
2742
3.66 KIPS |
|
Text Classification (HP)
|
100% |
4978
6.64 KIPS |
|
Text Classification (Q)
|
93% |
4952
6.65 KIPS |
|
Machine Translation (SP)
|
100% |
5781
99.6 IPS |
|
Machine Translation (HP)
|
100% |
4969
85.6 IPS |
|
Machine Translation (Q)
|
98% |
5427
93.8 IPS |