User | edsonchan |
Upload Date | August 16 2024 05:42 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
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 | 3.64 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1480
275.3 IPS |
|
Image Classification (HP)
|
100% |
1834
341.1 IPS |
|
Image Classification (Q)
|
99% |
1824
340.3 IPS |
|
Image Segmentation (SP)
|
100% |
1328
21.5 IPS |
|
Image Segmentation (HP)
|
100% |
1349
21.9 IPS |
|
Image Segmentation (Q)
|
100% |
1356
22.0 IPS |
|
Pose Estimation (SP)
|
100% |
6278
7.33 IPS |
|
Pose Estimation (HP)
|
100% |
14755
17.2 IPS |
|
Pose Estimation (Q)
|
96% |
12552
14.7 IPS |
|
Object Detection (SP)
|
100% |
1575
124.9 IPS |
|
Object Detection (HP)
|
97% |
2229
177.4 IPS |
|
Object Detection (Q)
|
94% |
1721
137.2 IPS |
|
Face Detection (SP)
|
100% |
2915
34.6 IPS |
|
Face Detection (HP)
|
100% |
3926
46.7 IPS |
|
Face Detection (Q)
|
100% |
2845
33.8 IPS |
|
Depth Estimation (SP)
|
100% |
5535
42.6 IPS |
|
Depth Estimation (HP)
|
99% |
8626
66.7 IPS |
|
Depth Estimation (Q)
|
96% |
3964
30.7 IPS |
|
Style Transfer (SP)
|
100% |
16930
21.8 IPS |
|
Style Transfer (HP)
|
100% |
26879
34.6 IPS |
|
Style Transfer (Q)
|
100% |
26722
34.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3816
140.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
4886
180.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
3580
132.6 IPS |
|
Text Classification (SP)
|
100% |
2282
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3421
4.57 KIPS |
|
Text Classification (Q)
|
93% |
3390
4.55 KIPS |
|
Machine Translation (SP)
|
100% |
2288
39.4 IPS |
|
Machine Translation (HP)
|
98% |
4613
79.7 IPS |
|
Machine Translation (Q)
|
98% |
4399
76.0 IPS |