User | dipak |
Upload Date | December 04 2024 12:15 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 3.47 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1458
271.1 IPS |
|
Image Classification (HP)
|
100% |
13669
2.54 KIPS |
|
Image Classification (Q)
|
96% |
16140
3.01 KIPS |
|
Image Segmentation (SP)
|
100% |
1772
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
19351
313.7 IPS |
|
Image Segmentation (Q)
|
99% |
24373
395.1 IPS |
|
Pose Estimation (SP)
|
100% |
18303
21.4 IPS |
|
Pose Estimation (HP)
|
100% |
105199
122.8 IPS |
|
Pose Estimation (Q)
|
95% |
103949
121.8 IPS |
|
Object Detection (SP)
|
100% |
1848
146.6 IPS |
|
Object Detection (HP)
|
99% |
15692
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17570
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3747
44.5 IPS |
|
Face Detection (HP)
|
100% |
36310
431.4 IPS |
|
Face Detection (Q)
|
100% |
46235
549.4 IPS |
|
Depth Estimation (SP)
|
100% |
6348
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
85743
660.6 IPS |
|
Depth Estimation (Q)
|
85% |
107823
842.6 IPS |
|
Style Transfer (SP)
|
100% |
27143
34.9 IPS |
|
Style Transfer (HP)
|
100% |
202418
260.2 IPS |
|
Style Transfer (Q)
|
96% |
193313
249.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
6005
221.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
40624
1.50 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47458
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2341
3.13 KIPS |
|
Text Classification (HP)
|
100% |
4023
5.37 KIPS |
|
Text Classification (Q)
|
93% |
4032
5.41 KIPS |
|
Machine Translation (SP)
|
100% |
4852
83.6 IPS |
|
Machine Translation (HP)
|
100% |
3765
64.9 IPS |
|
Machine Translation (Q)
|
98% |
4851
83.8 IPS |