User | edwardhchan |
Upload Date | August 16 2024 01:09 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
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 | 3.21 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1322
245.8 IPS |
|
Image Classification (HP)
|
100% |
6839
1.27 KIPS |
|
Image Classification (Q)
|
99% |
7242
1.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1628
26.4 IPS |
|
Image Segmentation (HP)
|
100% |
5900
95.6 IPS |
|
Image Segmentation (Q)
|
100% |
5902
95.7 IPS |
|
Pose Estimation (SP)
|
100% |
10977
12.8 IPS |
|
Pose Estimation (HP)
|
100% |
69116
80.6 IPS |
|
Pose Estimation (Q)
|
94% |
65573
76.9 IPS |
|
Object Detection (SP)
|
100% |
1588
126.0 IPS |
|
Object Detection (HP)
|
99% |
7202
572.9 IPS |
|
Object Detection (Q)
|
91% |
7144
570.8 IPS |
|
Face Detection (SP)
|
100% |
3288
39.1 IPS |
|
Face Detection (HP)
|
100% |
11923
141.7 IPS |
|
Face Detection (Q)
|
100% |
12576
149.4 IPS |
|
Depth Estimation (SP)
|
100% |
5914
45.6 IPS |
|
Depth Estimation (HP)
|
99% |
45186
348.1 IPS |
|
Depth Estimation (Q)
|
97% |
48637
376.1 IPS |
|
Style Transfer (SP)
|
100% |
22349
28.7 IPS |
|
Style Transfer (HP)
|
100% |
116643
149.9 IPS |
|
Style Transfer (Q)
|
100% |
121546
156.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4303
158.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25380
937.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
27351
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2203
2.94 KIPS |
|
Text Classification (HP)
|
100% |
3698
4.94 KIPS |
|
Text Classification (Q)
|
93% |
3738
5.02 KIPS |
|
Machine Translation (SP)
|
100% |
3363
57.9 IPS |
|
Machine Translation (HP)
|
100% |
1866
32.1 IPS |
|
Machine Translation (Q)
|
98% |
1819
31.4 IPS |