User | non |
Upload Date | August 18 2024 03:20 PM |
Views | 9 |
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 | 3.47 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1446
268.9 IPS |
|
Image Classification (HP)
|
100% |
13547
2.52 KIPS |
|
Image Classification (Q)
|
99% |
15196
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1744
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
9284
150.5 IPS |
|
Image Segmentation (Q)
|
100% |
9272
150.3 IPS |
|
Pose Estimation (SP)
|
100% |
18834
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
103264
120.5 IPS |
|
Pose Estimation (Q)
|
94% |
99316
116.5 IPS |
|
Object Detection (SP)
|
100% |
1822
144.6 IPS |
|
Object Detection (HP)
|
99% |
14185
1.13 KIPS |
|
Object Detection (Q)
|
91% |
17158
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3663
43.5 IPS |
|
Face Detection (HP)
|
100% |
23733
282.0 IPS |
|
Face Detection (Q)
|
100% |
36912
438.6 IPS |
|
Depth Estimation (SP)
|
100% |
6397
49.3 IPS |
|
Depth Estimation (HP)
|
99% |
72713
560.2 IPS |
|
Depth Estimation (Q)
|
97% |
80942
625.9 IPS |
|
Style Transfer (SP)
|
100% |
28529
36.7 IPS |
|
Style Transfer (HP)
|
100% |
156760
201.5 IPS |
|
Style Transfer (Q)
|
100% |
156245
200.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5879
217.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
40010
1.48 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47446
1.76 KIPS |
|
Text Classification (SP)
|
100% |
2240
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3878
5.18 KIPS |
|
Text Classification (Q)
|
93% |
3871
5.19 KIPS |
|
Machine Translation (SP)
|
100% |
4965
85.5 IPS |
|
Machine Translation (HP)
|
100% |
2032
35.0 IPS |
|
Machine Translation (Q)
|
98% |
2023
35.0 IPS |