Upload Date | September 19 2024 07:22 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% |
1340
249.1 IPS |
|
Image Classification (HP)
|
100% |
6752
1.26 KIPS |
|
Image Classification (Q)
|
99% |
7245
1.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1593
25.8 IPS |
|
Image Segmentation (HP)
|
100% |
5905
95.7 IPS |
|
Image Segmentation (Q)
|
100% |
5902
95.7 IPS |
|
Pose Estimation (SP)
|
100% |
11056
12.9 IPS |
|
Pose Estimation (HP)
|
100% |
69261
80.8 IPS |
|
Pose Estimation (Q)
|
94% |
64651
75.8 IPS |
|
Object Detection (SP)
|
100% |
1593
126.4 IPS |
|
Object Detection (HP)
|
99% |
7297
580.4 IPS |
|
Object Detection (Q)
|
91% |
7342
586.7 IPS |
|
Face Detection (SP)
|
100% |
3281
39.0 IPS |
|
Face Detection (HP)
|
100% |
12056
143.3 IPS |
|
Face Detection (Q)
|
100% |
13412
159.4 IPS |
|
Depth Estimation (SP)
|
100% |
5971
46.0 IPS |
|
Depth Estimation (HP)
|
99% |
45915
353.7 IPS |
|
Depth Estimation (Q)
|
97% |
49307
381.3 IPS |
|
Style Transfer (SP)
|
100% |
22387
28.8 IPS |
|
Style Transfer (HP)
|
100% |
117283
150.8 IPS |
|
Style Transfer (Q)
|
100% |
122483
157.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4357
160.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25819
953.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
27465
1.02 KIPS |
|
Text Classification (SP)
|
100% |
2269
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3825
5.11 KIPS |
|
Text Classification (Q)
|
93% |
3860
5.18 KIPS |
|
Machine Translation (SP)
|
100% |
3422
59.0 IPS |
|
Machine Translation (HP)
|
100% |
1895
32.6 IPS |
|
Machine Translation (Q)
|
98% |
1887
32.6 IPS |