Upload Date | September 19 2024 07:29 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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% |
4391
816.7 IPS |
|
Image Classification (HP)
|
100% |
4407
819.5 IPS |
|
Image Classification (Q)
|
99% |
3851
718.3 IPS |
|
Image Segmentation (SP)
|
100% |
8617
139.7 IPS |
|
Image Segmentation (HP)
|
100% |
8532
138.3 IPS |
|
Image Segmentation (Q)
|
100% |
8227
133.4 IPS |
|
Pose Estimation (SP)
|
100% |
47269
55.2 IPS |
|
Pose Estimation (HP)
|
100% |
49409
57.7 IPS |
|
Pose Estimation (Q)
|
97% |
42879
50.2 IPS |
|
Object Detection (SP)
|
100% |
3591
284.8 IPS |
|
Object Detection (HP)
|
100% |
3816
302.7 IPS |
|
Object Detection (Q)
|
91% |
3723
297.5 IPS |
|
Face Detection (SP)
|
100% |
13344
158.6 IPS |
|
Face Detection (HP)
|
100% |
14177
168.5 IPS |
|
Face Detection (Q)
|
100% |
12890
153.2 IPS |
|
Depth Estimation (SP)
|
100% |
23582
181.7 IPS |
|
Depth Estimation (HP)
|
99% |
24201
186.5 IPS |
|
Depth Estimation (Q)
|
97% |
4948
38.3 IPS |
|
Style Transfer (SP)
|
100% |
80640
103.7 IPS |
|
Style Transfer (HP)
|
100% |
95289
122.5 IPS |
|
Style Transfer (Q)
|
100% |
93377
120.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
15741
581.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
15818
584.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
11122
412.0 IPS |
|
Text Classification (SP)
|
100% |
2263
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3843
5.13 KIPS |
|
Text Classification (Q)
|
93% |
3848
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
1028
17.7 IPS |
|
Machine Translation (HP)
|
100% |
1017
17.5 IPS |
|
Machine Translation (Q)
|
98% |
1035
17.9 IPS |