User | wave |
Upload Date | November 09 2024 06:09 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
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 | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1392
258.8 IPS |
|
Image Classification (HP)
|
100% |
13743
2.56 KIPS |
|
Image Classification (Q)
|
96% |
17039
3.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1709
27.7 IPS |
|
Image Segmentation (HP)
|
100% |
19584
317.5 IPS |
|
Image Segmentation (Q)
|
99% |
24407
395.7 IPS |
|
Pose Estimation (SP)
|
100% |
13021
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
105982
123.7 IPS |
|
Pose Estimation (Q)
|
95% |
104168
122.1 IPS |
|
Object Detection (SP)
|
100% |
1703
135.1 IPS |
|
Object Detection (HP)
|
99% |
15170
1.21 KIPS |
|
Object Detection (Q)
|
91% |
16830
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3765
44.7 IPS |
|
Face Detection (HP)
|
100% |
35166
417.9 IPS |
|
Face Detection (Q)
|
100% |
44139
524.5 IPS |
|
Depth Estimation (SP)
|
100% |
6460
49.8 IPS |
|
Depth Estimation (HP)
|
99% |
87638
675.2 IPS |
|
Depth Estimation (Q)
|
85% |
107859
842.9 IPS |
|
Style Transfer (SP)
|
100% |
24749
31.8 IPS |
|
Style Transfer (HP)
|
100% |
203602
261.7 IPS |
|
Style Transfer (Q)
|
96% |
190447
245.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5047
186.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
41055
1.52 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48968
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2288
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3898
5.20 KIPS |
|
Text Classification (Q)
|
93% |
3815
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
4601
79.3 IPS |
|
Machine Translation (HP)
|
100% |
3940
67.9 IPS |
|
Machine Translation (Q)
|
98% |
4173
72.1 IPS |