User | rene_simon |
Upload Date | August 16 2024 08:38 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1091
202.9 IPS |
|
Image Classification (HP)
|
100% |
8059
1.50 KIPS |
|
Image Classification (Q)
|
99% |
8645
1.61 KIPS |
|
Image Segmentation (SP)
|
100% |
726
11.8 IPS |
|
Image Segmentation (HP)
|
100% |
5127
83.1 IPS |
|
Image Segmentation (Q)
|
100% |
5166
83.7 IPS |
|
Pose Estimation (SP)
|
100% |
11179
13.0 IPS |
|
Pose Estimation (HP)
|
100% |
92888
108.4 IPS |
|
Pose Estimation (Q)
|
94% |
89243
104.7 IPS |
|
Object Detection (SP)
|
100% |
1240
98.3 IPS |
|
Object Detection (HP)
|
99% |
9459
752.5 IPS |
|
Object Detection (Q)
|
93% |
10285
820.7 IPS |
|
Face Detection (SP)
|
100% |
1995
23.7 IPS |
|
Face Detection (HP)
|
100% |
11711
139.2 IPS |
|
Face Detection (Q)
|
100% |
13979
166.1 IPS |
|
Depth Estimation (SP)
|
100% |
4174
32.2 IPS |
|
Depth Estimation (HP)
|
99% |
56729
437.1 IPS |
|
Depth Estimation (Q)
|
97% |
61308
474.0 IPS |
|
Style Transfer (SP)
|
100% |
13464
17.3 IPS |
|
Style Transfer (HP)
|
100% |
146413
188.2 IPS |
|
Style Transfer (Q)
|
100% |
147271
189.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3059
113.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
21055
777.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
28248
1.05 KIPS |
|
Text Classification (SP)
|
100% |
1007
1.34 KIPS |
|
Text Classification (HP)
|
100% |
4172
5.57 KIPS |
|
Text Classification (Q)
|
93% |
3938
5.28 KIPS |
|
Machine Translation (SP)
|
100% |
1891
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2035
35.1 IPS |
|
Machine Translation (Q)
|
98% |
1952
33.7 IPS |