User | anthonynelzin |
Upload Date | March 13 2025 09:25 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% |
15237
2.83 KIPS |
|
Image Classification (Q)
|
97% |
16387
3.06 KIPS |
|
Image Segmentation (SP)
|
100% |
2082
33.7 IPS |
|
Image Segmentation (HP)
|
100% |
21543
349.2 IPS |
|
Image Segmentation (Q)
|
99% |
26711
433.0 IPS |
|
Pose Estimation (SP)
|
100% |
20599
24.0 IPS |
|
Pose Estimation (HP)
|
100% |
120573
140.7 IPS |
|
Pose Estimation (Q)
|
95% |
118740
139.2 IPS |
|
Object Detection (SP)
|
100% |
2166
171.8 IPS |
|
Object Detection (HP)
|
100% |
17432
1.38 KIPS |
|
Object Detection (Q)
|
91% |
17248
1.38 KIPS |
|
Face Detection (SP)
|
100% |
4635
55.1 IPS |
|
Face Detection (HP)
|
100% |
37398
444.4 IPS |
|
Face Detection (Q)
|
100% |
47495
564.3 IPS |
|
Depth Estimation (SP)
|
100% |
8062
62.1 IPS |
|
Depth Estimation (HP)
|
99% |
102651
790.9 IPS |
|
Depth Estimation (Q)
|
85% |
118727
928.3 IPS |
|
Style Transfer (SP)
|
100% |
33358
42.9 IPS |
|
Style Transfer (HP)
|
100% |
219067
281.6 IPS |
|
Style Transfer (Q)
|
96% |
213100
275.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6908
255.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
37805
1.40 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48697
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2654
3.54 KIPS |
|
Text Classification (HP)
|
100% |
4846
6.47 KIPS |
|
Text Classification (Q)
|
93% |
4829
6.48 KIPS |
|
Machine Translation (SP)
|
100% |
5872
101.2 IPS |
|
Machine Translation (HP)
|
100% |
4578
78.9 IPS |
|
Machine Translation (Q)
|
98% |
4913
84.9 IPS |