User | l3uzz |
Upload Date | October 07 2024 11:57 PM |
Views | 13 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
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 | 3.66 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1470
273.3 IPS |
|
Image Classification (HP)
|
100% |
13592
2.53 KIPS |
|
Image Classification (Q)
|
96% |
6502
1.21 KIPS |
|
Image Segmentation (SP)
|
100% |
1802
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
10205
165.4 IPS |
|
Image Segmentation (Q)
|
99% |
11349
184.0 IPS |
|
Pose Estimation (SP)
|
100% |
18477
21.6 IPS |
|
Pose Estimation (HP)
|
100% |
105425
123.0 IPS |
|
Pose Estimation (Q)
|
95% |
103559
121.4 IPS |
|
Object Detection (SP)
|
100% |
1872
148.5 IPS |
|
Object Detection (HP)
|
99% |
15891
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17525
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3665
43.6 IPS |
|
Face Detection (HP)
|
100% |
35847
425.9 IPS |
|
Face Detection (Q)
|
100% |
45768
543.8 IPS |
|
Depth Estimation (SP)
|
100% |
6527
50.3 IPS |
|
Depth Estimation (HP)
|
99% |
85757
660.7 IPS |
|
Depth Estimation (Q)
|
85% |
106743
834.1 IPS |
|
Style Transfer (SP)
|
100% |
28515
36.7 IPS |
|
Style Transfer (HP)
|
100% |
202919
260.9 IPS |
|
Style Transfer (Q)
|
96% |
189077
244.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6019
222.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
39908
1.47 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48327
1.78 KIPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
4018
5.36 KIPS |
|
Text Classification (Q)
|
93% |
3986
5.35 KIPS |
|
Machine Translation (SP)
|
100% |
5048
87.0 IPS |
|
Machine Translation (HP)
|
100% |
2113
36.4 IPS |
|
Machine Translation (Q)
|
98% |
2112
36.5 IPS |