User | KeviNW000 |
Upload Date | November 10 2024 08:42 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
Model | Mac Studio (2023) |
Model ID | Mac14,13 |
Motherboard | Mac14,13 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1410
262.1 IPS |
|
Image Classification (HP)
|
100% |
13085
2.43 KIPS |
|
Image Classification (Q)
|
99% |
15944
2.97 KIPS |
|
Image Segmentation (SP)
|
100% |
1701
27.6 IPS |
|
Image Segmentation (HP)
|
100% |
15725
254.9 IPS |
|
Image Segmentation (Q)
|
100% |
15784
255.9 IPS |
|
Pose Estimation (SP)
|
100% |
12944
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
103160
120.4 IPS |
|
Pose Estimation (Q)
|
94% |
99981
117.3 IPS |
|
Object Detection (SP)
|
100% |
1691
134.1 IPS |
|
Object Detection (HP)
|
99% |
14045
1.12 KIPS |
|
Object Detection (Q)
|
91% |
16958
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3719
44.2 IPS |
|
Face Detection (HP)
|
100% |
23748
282.2 IPS |
|
Face Detection (Q)
|
100% |
36956
439.1 IPS |
|
Depth Estimation (SP)
|
100% |
6395
49.3 IPS |
|
Depth Estimation (HP)
|
99% |
73662
567.5 IPS |
|
Depth Estimation (Q)
|
97% |
82324
636.5 IPS |
|
Style Transfer (SP)
|
100% |
24968
32.1 IPS |
|
Style Transfer (HP)
|
100% |
158407
203.6 IPS |
|
Style Transfer (Q)
|
100% |
157876
203.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5087
187.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
40728
1.50 KIPS |
|
Image Super-Resolution (Q)
|
98% |
48717
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2295
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3843
5.13 KIPS |
|
Text Classification (Q)
|
93% |
3842
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
4632
79.8 IPS |
|
Machine Translation (HP)
|
100% |
3944
67.9 IPS |
|
Machine Translation (Q)
|
98% |
4184
72.3 IPS |