User | compaqdrew |
Upload Date | August 18 2024 10:51 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
906
168.4 IPS |
|
Image Classification (HP)
|
100% |
7137
1.33 KIPS |
|
Image Classification (Q)
|
99% |
7505
1.40 KIPS |
|
Image Segmentation (SP)
|
100% |
656
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
3889
63.0 IPS |
|
Image Segmentation (Q)
|
100% |
3879
62.9 IPS |
|
Pose Estimation (SP)
|
100% |
9863
11.5 IPS |
|
Pose Estimation (HP)
|
100% |
69061
80.6 IPS |
|
Pose Estimation (Q)
|
94% |
65693
77.1 IPS |
|
Object Detection (SP)
|
100% |
999
79.2 IPS |
|
Object Detection (HP)
|
99% |
7476
594.7 IPS |
|
Object Detection (Q)
|
93% |
7133
569.1 IPS |
|
Face Detection (SP)
|
100% |
1656
19.7 IPS |
|
Face Detection (HP)
|
100% |
11559
137.4 IPS |
|
Face Detection (Q)
|
100% |
11006
130.8 IPS |
|
Depth Estimation (SP)
|
100% |
3154
24.3 IPS |
|
Depth Estimation (HP)
|
99% |
45917
353.8 IPS |
|
Depth Estimation (Q)
|
97% |
49547
383.1 IPS |
|
Style Transfer (SP)
|
100% |
12192
15.7 IPS |
|
Style Transfer (HP)
|
100% |
118046
151.8 IPS |
|
Style Transfer (Q)
|
100% |
122968
158.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2367
87.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
18666
689.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
22966
850.9 IPS |
|
Text Classification (SP)
|
100% |
483
645.0 IPS |
|
Text Classification (HP)
|
100% |
3556
4.75 KIPS |
|
Text Classification (Q)
|
93% |
3432
4.61 KIPS |
|
Machine Translation (SP)
|
100% |
1560
26.9 IPS |
|
Machine Translation (HP)
|
100% |
1906
32.8 IPS |
|
Machine Translation (Q)
|
98% |
1883
32.5 IPS |