User | non |
Upload Date | August 16 2024 09:57 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 3.46 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1449
269.5 IPS |
|
Image Classification (HP)
|
100% |
12645
2.35 KIPS |
|
Image Classification (Q)
|
99% |
14724
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1770
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
9252
150.0 IPS |
|
Image Segmentation (Q)
|
100% |
9266
150.2 IPS |
|
Pose Estimation (SP)
|
100% |
18259
21.3 IPS |
|
Pose Estimation (HP)
|
100% |
101956
119.0 IPS |
|
Pose Estimation (Q)
|
94% |
96742
113.5 IPS |
|
Object Detection (SP)
|
100% |
1847
146.5 IPS |
|
Object Detection (HP)
|
99% |
14253
1.13 KIPS |
|
Object Detection (Q)
|
91% |
17112
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3608
42.9 IPS |
|
Face Detection (HP)
|
100% |
23734
282.0 IPS |
|
Face Detection (Q)
|
100% |
36751
436.7 IPS |
|
Depth Estimation (SP)
|
100% |
6390
49.2 IPS |
|
Depth Estimation (HP)
|
99% |
72307
557.1 IPS |
|
Depth Estimation (Q)
|
97% |
81065
626.8 IPS |
|
Style Transfer (SP)
|
100% |
27597
35.5 IPS |
|
Style Transfer (HP)
|
100% |
156969
201.8 IPS |
|
Style Transfer (Q)
|
100% |
156298
200.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5953
219.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
38834
1.43 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47194
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2238
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3844
5.13 KIPS |
|
Text Classification (Q)
|
93% |
3857
5.18 KIPS |
|
Machine Translation (SP)
|
100% |
4984
85.8 IPS |
|
Machine Translation (HP)
|
100% |
2023
34.8 IPS |
|
Machine Translation (Q)
|
98% |
2012
34.8 IPS |