User | unixwizard |
Upload Date | December 10 2024 01:59 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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 | 3.67 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1392
258.9 IPS |
|
Image Classification (HP)
|
100% |
14300
2.66 KIPS |
|
Image Classification (Q)
|
96% |
16408
3.06 KIPS |
|
Image Segmentation (SP)
|
100% |
1682
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
19402
314.5 IPS |
|
Image Segmentation (Q)
|
99% |
24499
397.1 IPS |
|
Pose Estimation (SP)
|
100% |
12817
15.0 IPS |
|
Pose Estimation (HP)
|
100% |
106011
123.7 IPS |
|
Pose Estimation (Q)
|
95% |
104216
122.1 IPS |
|
Object Detection (SP)
|
100% |
1678
133.1 IPS |
|
Object Detection (HP)
|
99% |
15860
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17182
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3591
42.7 IPS |
|
Face Detection (HP)
|
100% |
35912
426.7 IPS |
|
Face Detection (Q)
|
100% |
41148
488.9 IPS |
|
Depth Estimation (SP)
|
100% |
6266
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
87633
675.2 IPS |
|
Depth Estimation (Q)
|
85% |
109420
855.1 IPS |
|
Style Transfer (SP)
|
100% |
25105
32.3 IPS |
|
Style Transfer (HP)
|
100% |
204610
263.0 IPS |
|
Style Transfer (Q)
|
96% |
191725
247.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5086
187.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
41760
1.54 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50455
1.86 KIPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
4026
5.37 KIPS |
|
Text Classification (Q)
|
93% |
3979
5.34 KIPS |
|
Machine Translation (SP)
|
100% |
4076
70.2 IPS |
|
Machine Translation (HP)
|
100% |
5160
88.9 IPS |
|
Machine Translation (Q)
|
98% |
5682
98.2 IPS |