User | mprimeaux |
Upload Date | August 15 2024 05:15 PM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
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 | 3.64 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1110
206.4 IPS |
|
Image Classification (HP)
|
100% |
1006
187.1 IPS |
|
Image Classification (Q)
|
99% |
1036
193.2 IPS |
|
Image Segmentation (SP)
|
100% |
16694
270.6 IPS |
|
Image Segmentation (HP)
|
100% |
17181
278.5 IPS |
|
Image Segmentation (Q)
|
100% |
16169
262.1 IPS |
|
Pose Estimation (SP)
|
100% |
135045
157.6 IPS |
|
Pose Estimation (HP)
|
100% |
138935
162.1 IPS |
|
Pose Estimation (Q)
|
96% |
118026
138.3 IPS |
|
Object Detection (SP)
|
100% |
6012
476.8 IPS |
|
Object Detection (HP)
|
100% |
6077
482.1 IPS |
|
Object Detection (Q)
|
92% |
4964
396.2 IPS |
|
Face Detection (SP)
|
100% |
29863
354.8 IPS |
|
Face Detection (HP)
|
100% |
30535
362.8 IPS |
|
Face Detection (Q)
|
100% |
22479
267.1 IPS |
|
Depth Estimation (SP)
|
100% |
34543
266.1 IPS |
|
Depth Estimation (HP)
|
99% |
36356
280.1 IPS |
|
Depth Estimation (Q)
|
97% |
36193
279.8 IPS |
|
Style Transfer (SP)
|
100% |
221701
285.0 IPS |
|
Style Transfer (HP)
|
100% |
226689
291.4 IPS |
|
Style Transfer (Q)
|
100% |
209984
269.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
25501
941.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
25935
957.7 IPS |
|
Image Super-Resolution (Q)
|
98% |
18218
675.0 IPS |
|
Text Classification (SP)
|
100% |
938
1.25 KIPS |
|
Text Classification (HP)
|
100% |
739
986.0 IPS |
|
Text Classification (Q)
|
93% |
624
837.5 IPS |
|
Machine Translation (SP)
|
100% |
1946
33.5 IPS |
|
Machine Translation (HP)
|
96% |
2086
36.1 IPS |
|
Machine Translation (Q)
|
98% |
2089
36.1 IPS |