Upload Date | September 19 2024 07:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
Model | Mac Studio |
Model ID | Mac13,1 |
Motherboard | Mac13,1 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1347
250.4 IPS |
|
Image Classification (HP)
|
100% |
6761
1.26 KIPS |
|
Image Classification (Q)
|
99% |
7406
1.38 KIPS |
|
Image Segmentation (SP)
|
100% |
1608
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
5902
95.7 IPS |
|
Image Segmentation (Q)
|
100% |
5906
95.7 IPS |
|
Pose Estimation (SP)
|
100% |
11126
13.0 IPS |
|
Pose Estimation (HP)
|
100% |
69316
80.9 IPS |
|
Pose Estimation (Q)
|
94% |
64806
76.0 IPS |
|
Object Detection (SP)
|
100% |
1592
126.3 IPS |
|
Object Detection (HP)
|
99% |
7281
579.2 IPS |
|
Object Detection (Q)
|
91% |
7391
590.6 IPS |
|
Face Detection (SP)
|
100% |
3282
39.0 IPS |
|
Face Detection (HP)
|
100% |
11995
142.5 IPS |
|
Face Detection (Q)
|
100% |
13622
161.9 IPS |
|
Depth Estimation (SP)
|
100% |
5903
45.5 IPS |
|
Depth Estimation (HP)
|
99% |
45700
352.1 IPS |
|
Depth Estimation (Q)
|
97% |
49171
380.2 IPS |
|
Style Transfer (SP)
|
100% |
22395
28.8 IPS |
|
Style Transfer (HP)
|
100% |
117479
151.0 IPS |
|
Style Transfer (Q)
|
100% |
122678
157.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4336
160.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
25895
956.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
27772
1.03 KIPS |
|
Text Classification (SP)
|
100% |
2267
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3828
5.11 KIPS |
|
Text Classification (Q)
|
93% |
3806
5.11 KIPS |
|
Machine Translation (SP)
|
100% |
3405
58.7 IPS |
|
Machine Translation (HP)
|
100% |
1894
32.6 IPS |
|
Machine Translation (Q)
|
98% |
1894
32.7 IPS |