User | Nicktenn |
Upload Date | August 15 2024 05:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1387
257.9 IPS |
|
Image Classification (HP)
|
100% |
2240
416.5 IPS |
|
Image Classification (Q)
|
99% |
2233
416.4 IPS |
|
Image Segmentation (SP)
|
100% |
1679
27.2 IPS |
|
Image Segmentation (HP)
|
100% |
2647
42.9 IPS |
|
Image Segmentation (Q)
|
100% |
2636
42.7 IPS |
|
Pose Estimation (SP)
|
100% |
13113
15.3 IPS |
|
Pose Estimation (HP)
|
100% |
25015
29.2 IPS |
|
Pose Estimation (Q)
|
96% |
18452
21.6 IPS |
|
Object Detection (SP)
|
100% |
1704
135.1 IPS |
|
Object Detection (HP)
|
97% |
2750
218.9 IPS |
|
Object Detection (Q)
|
94% |
1973
157.2 IPS |
|
Face Detection (SP)
|
100% |
3598
42.7 IPS |
|
Face Detection (HP)
|
100% |
5960
70.8 IPS |
|
Face Detection (Q)
|
100% |
3387
40.2 IPS |
|
Depth Estimation (SP)
|
100% |
6263
48.3 IPS |
|
Depth Estimation (HP)
|
98% |
12282
94.9 IPS |
|
Depth Estimation (Q)
|
97% |
12180
94.2 IPS |
|
Style Transfer (SP)
|
100% |
24863
32.0 IPS |
|
Style Transfer (HP)
|
100% |
38631
49.7 IPS |
|
Style Transfer (Q)
|
100% |
38885
50.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5198
191.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
6875
253.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
4380
162.3 IPS |
|
Text Classification (SP)
|
100% |
2293
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3933
5.25 KIPS |
|
Text Classification (Q)
|
93% |
3905
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
4591
79.1 IPS |
|
Machine Translation (HP)
|
98% |
6554
113.2 IPS |
|
Machine Translation (Q)
|
98% |
6500
112.3 IPS |