User | non |
Upload Date | August 18 2024 09:20 AM |
Views | 7 |
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% |
1438
267.5 IPS |
|
Image Classification (HP)
|
100% |
13202
2.46 KIPS |
|
Image Classification (Q)
|
99% |
14860
2.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1745
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
9266
150.2 IPS |
|
Image Segmentation (Q)
|
100% |
9269
150.3 IPS |
|
Pose Estimation (SP)
|
100% |
18905
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
102095
119.1 IPS |
|
Pose Estimation (Q)
|
94% |
97159
114.0 IPS |
|
Object Detection (SP)
|
100% |
1836
145.6 IPS |
|
Object Detection (HP)
|
99% |
14249
1.13 KIPS |
|
Object Detection (Q)
|
91% |
17187
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3747
44.5 IPS |
|
Face Detection (HP)
|
100% |
23414
278.2 IPS |
|
Face Detection (Q)
|
100% |
36577
434.6 IPS |
|
Depth Estimation (SP)
|
100% |
6307
48.6 IPS |
|
Depth Estimation (HP)
|
99% |
72519
558.7 IPS |
|
Depth Estimation (Q)
|
97% |
80886
625.4 IPS |
|
Style Transfer (SP)
|
100% |
28589
36.8 IPS |
|
Style Transfer (HP)
|
100% |
156078
200.6 IPS |
|
Style Transfer (Q)
|
100% |
156585
201.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5929
218.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
39973
1.48 KIPS |
|
Image Super-Resolution (Q)
|
98% |
45995
1.70 KIPS |
|
Text Classification (SP)
|
100% |
2235
2.98 KIPS |
|
Text Classification (HP)
|
100% |
3873
5.17 KIPS |
|
Text Classification (Q)
|
93% |
3852
5.17 KIPS |
|
Machine Translation (SP)
|
100% |
4969
85.6 IPS |
|
Machine Translation (HP)
|
100% |
2031
35.0 IPS |
|
Machine Translation (Q)
|
98% |
2020
34.9 IPS |