User | tokris |
Upload Date | February 15 2025 05:40 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 3.65 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7045
1.31 KIPS |
|
Image Classification (HP)
|
100% |
7171
1.33 KIPS |
|
Image Classification (Q)
|
97% |
6175
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
14134
229.1 IPS |
|
Image Segmentation (HP)
|
100% |
13882
225.0 IPS |
|
Image Segmentation (Q)
|
99% |
13687
221.9 IPS |
|
Pose Estimation (SP)
|
100% |
84472
98.6 IPS |
|
Pose Estimation (HP)
|
100% |
88249
103.0 IPS |
|
Pose Estimation (Q)
|
95% |
82771
97.0 IPS |
|
Object Detection (SP)
|
100% |
6665
528.7 IPS |
|
Object Detection (HP)
|
100% |
6960
552.1 IPS |
|
Object Detection (Q)
|
91% |
6067
484.8 IPS |
|
Face Detection (SP)
|
100% |
28699
341.0 IPS |
|
Face Detection (HP)
|
100% |
29895
355.2 IPS |
|
Face Detection (Q)
|
100% |
21784
258.8 IPS |
|
Depth Estimation (SP)
|
100% |
34327
264.5 IPS |
|
Depth Estimation (HP)
|
99% |
34854
268.5 IPS |
|
Depth Estimation (Q)
|
85% |
29659
231.8 IPS |
|
Style Transfer (SP)
|
100% |
137437
176.7 IPS |
|
Style Transfer (HP)
|
100% |
155284
199.6 IPS |
|
Style Transfer (Q)
|
96% |
144725
186.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
20859
770.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
21444
791.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
17418
643.2 IPS |
|
Text Classification (SP)
|
100% |
2296
3.07 KIPS |
|
Text Classification (HP)
|
100% |
4057
5.42 KIPS |
|
Text Classification (Q)
|
93% |
4040
5.42 KIPS |
|
Machine Translation (SP)
|
100% |
2374
40.9 IPS |
|
Machine Translation (HP)
|
100% |
2269
39.1 IPS |
|
Machine Translation (Q)
|
98% |
2263
39.1 IPS |