User | tphillips63 |
Upload Date | October 29 2024 08:46 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac Studio (2023) |
Model ID | Mac14,14 |
Motherboard | Mac14,14 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.67 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6313
1.17 KIPS |
|
Image Classification (HP)
|
100% |
6466
1.20 KIPS |
|
Image Classification (Q)
|
97% |
5682
1.06 KIPS |
|
Image Segmentation (SP)
|
100% |
17827
289.0 IPS |
|
Image Segmentation (HP)
|
100% |
18433
298.8 IPS |
|
Image Segmentation (Q)
|
99% |
19114
309.9 IPS |
|
Pose Estimation (SP)
|
100% |
138753
161.9 IPS |
|
Pose Estimation (HP)
|
100% |
142672
166.5 IPS |
|
Pose Estimation (Q)
|
95% |
130238
152.6 IPS |
|
Object Detection (SP)
|
100% |
6275
497.7 IPS |
|
Object Detection (HP)
|
100% |
6376
505.7 IPS |
|
Object Detection (Q)
|
91% |
5660
452.2 IPS |
|
Face Detection (SP)
|
100% |
35194
418.2 IPS |
|
Face Detection (HP)
|
100% |
35068
416.7 IPS |
|
Face Detection (Q)
|
100% |
28001
332.7 IPS |
|
Depth Estimation (SP)
|
100% |
35041
270.0 IPS |
|
Depth Estimation (HP)
|
99% |
36941
284.6 IPS |
|
Depth Estimation (Q)
|
85% |
31978
249.9 IPS |
|
Style Transfer (SP)
|
100% |
228349
293.5 IPS |
|
Style Transfer (HP)
|
100% |
230594
296.4 IPS |
|
Style Transfer (Q)
|
96% |
213051
274.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
25653
947.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
26261
969.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
21099
779.1 IPS |
|
Text Classification (SP)
|
100% |
2345
3.13 KIPS |
|
Text Classification (HP)
|
100% |
4049
5.40 KIPS |
|
Text Classification (Q)
|
93% |
4031
5.41 KIPS |
|
Machine Translation (SP)
|
100% |
2203
38.0 IPS |
|
Machine Translation (HP)
|
100% |
2164
37.3 IPS |
|
Machine Translation (Q)
|
98% |
2069
35.8 IPS |