User | enroscado |
Upload Date | April 29 2025 02:22 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
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 | 3.68 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1404
261.1 IPS |
|
Image Classification (HP)
|
100% |
2270
422.2 IPS |
|
Image Classification (Q)
|
96% |
1701
317.6 IPS |
|
Image Segmentation (SP)
|
100% |
1623
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
2483
40.3 IPS |
|
Image Segmentation (Q)
|
99% |
2940
47.7 IPS |
|
Pose Estimation (SP)
|
100% |
12989
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
24691
28.8 IPS |
|
Pose Estimation (Q)
|
95% |
19454
22.8 IPS |
|
Object Detection (SP)
|
100% |
1690
134.1 IPS |
|
Object Detection (HP)
|
97% |
2636
209.8 IPS |
|
Object Detection (Q)
|
94% |
2001
159.5 IPS |
|
Face Detection (SP)
|
100% |
3629
43.1 IPS |
|
Face Detection (HP)
|
100% |
5929
70.5 IPS |
|
Face Detection (Q)
|
100% |
3443
40.9 IPS |
|
Depth Estimation (SP)
|
100% |
6149
47.4 IPS |
|
Depth Estimation (HP)
|
98% |
11468
88.6 IPS |
|
Depth Estimation (Q)
|
85% |
7807
61.0 IPS |
|
Style Transfer (SP)
|
100% |
24853
31.9 IPS |
|
Style Transfer (HP)
|
100% |
38503
49.5 IPS |
|
Style Transfer (Q)
|
96% |
30522
39.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5078
187.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
6421
237.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
4516
166.8 IPS |
|
Text Classification (SP)
|
100% |
2353
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4091
5.46 KIPS |
|
Text Classification (Q)
|
93% |
4044
5.43 KIPS |
|
Machine Translation (SP)
|
100% |
4414
76.0 IPS |
|
Machine Translation (HP)
|
98% |
6642
114.8 IPS |
|
Machine Translation (Q)
|
98% |
6711
116.0 IPS |