Upload Date | November 09 2024 07:10 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac Studio |
Model ID | Mac13,2 |
Motherboard | Mac13,2 |
CPU Information | |
---|---|
Name | Apple M1 Ultra |
Topology | 1 Processor, 20 Cores |
Identifier | Apple M1 Ultra |
Base Frequency | 3.21 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4965
923.3 IPS |
|
Image Classification (HP)
|
100% |
4797
892.1 IPS |
|
Image Classification (Q)
|
97% |
4023
750.8 IPS |
|
Image Segmentation (SP)
|
100% |
11859
192.3 IPS |
|
Image Segmentation (HP)
|
100% |
11913
193.1 IPS |
|
Image Segmentation (Q)
|
99% |
11908
193.0 IPS |
|
Pose Estimation (SP)
|
100% |
81005
94.5 IPS |
|
Pose Estimation (HP)
|
100% |
84660
98.8 IPS |
|
Pose Estimation (Q)
|
95% |
77014
90.3 IPS |
|
Object Detection (SP)
|
100% |
4397
348.8 IPS |
|
Object Detection (HP)
|
100% |
4578
363.1 IPS |
|
Object Detection (Q)
|
91% |
4297
343.4 IPS |
|
Face Detection (SP)
|
100% |
23377
277.8 IPS |
|
Face Detection (HP)
|
100% |
23967
284.8 IPS |
|
Face Detection (Q)
|
100% |
16101
191.3 IPS |
|
Depth Estimation (SP)
|
100% |
26421
203.6 IPS |
|
Depth Estimation (HP)
|
99% |
26765
206.2 IPS |
|
Depth Estimation (Q)
|
85% |
22610
176.7 IPS |
|
Style Transfer (SP)
|
100% |
134989
173.5 IPS |
|
Style Transfer (HP)
|
100% |
150431
193.4 IPS |
|
Style Transfer (Q)
|
96% |
139374
179.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
15682
579.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
16059
593.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
12599
465.2 IPS |
|
Text Classification (SP)
|
100% |
2261
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3883
5.18 KIPS |
|
Text Classification (Q)
|
93% |
3916
5.26 KIPS |
|
Machine Translation (SP)
|
100% |
977
16.8 IPS |
|
Machine Translation (HP)
|
100% |
1001
17.2 IPS |
|
Machine Translation (Q)
|
98% |
922
15.9 IPS |