User | unixwizard |
Upload Date | February 10 2025 02:16 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
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 | 3.66 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1385
257.6 IPS |
|
Image Classification (HP)
|
100% |
14902
2.77 KIPS |
|
Image Classification (Q)
|
96% |
17416
3.25 KIPS |
|
Image Segmentation (SP)
|
100% |
1642
26.6 IPS |
|
Image Segmentation (HP)
|
100% |
19522
316.5 IPS |
|
Image Segmentation (Q)
|
99% |
24792
401.9 IPS |
|
Pose Estimation (SP)
|
100% |
12829
15.0 IPS |
|
Pose Estimation (HP)
|
100% |
106201
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
104451
122.4 IPS |
|
Object Detection (SP)
|
100% |
1662
131.8 IPS |
|
Object Detection (HP)
|
99% |
15798
1.26 KIPS |
|
Object Detection (Q)
|
91% |
17435
1.39 KIPS |
|
Face Detection (SP)
|
100% |
3553
42.2 IPS |
|
Face Detection (HP)
|
100% |
35454
421.3 IPS |
|
Face Detection (Q)
|
100% |
46304
550.2 IPS |
|
Depth Estimation (SP)
|
100% |
6374
49.1 IPS |
|
Depth Estimation (HP)
|
99% |
87540
674.4 IPS |
|
Depth Estimation (Q)
|
85% |
109542
856.0 IPS |
|
Style Transfer (SP)
|
100% |
25004
32.1 IPS |
|
Style Transfer (HP)
|
100% |
203353
261.4 IPS |
|
Style Transfer (Q)
|
96% |
191491
247.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5089
187.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
41110
1.52 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48853
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2288
3.05 KIPS |
|
Text Classification (HP)
|
100% |
4030
5.38 KIPS |
|
Text Classification (Q)
|
93% |
4023
5.40 KIPS |
|
Machine Translation (SP)
|
100% |
4607
79.4 IPS |
|
Machine Translation (HP)
|
100% |
4174
71.9 IPS |
|
Machine Translation (Q)
|
98% |
4366
75.4 IPS |