User | vincentoma |
Upload Date | August 27 2024 06:41 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,10 |
Motherboard | Mac15,10 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1167
216.9 IPS |
|
Image Classification (HP)
|
100% |
7422
1.38 KIPS |
|
Image Classification (Q)
|
99% |
7586
1.42 KIPS |
|
Image Segmentation (SP)
|
100% |
848
13.7 IPS |
|
Image Segmentation (HP)
|
100% |
6457
104.7 IPS |
|
Image Segmentation (Q)
|
100% |
6466
104.8 IPS |
|
Pose Estimation (SP)
|
100% |
15430
18.0 IPS |
|
Pose Estimation (HP)
|
100% |
103237
120.5 IPS |
|
Pose Estimation (Q)
|
94% |
98924
116.0 IPS |
|
Object Detection (SP)
|
100% |
1167
92.6 IPS |
|
Object Detection (HP)
|
100% |
9529
755.9 IPS |
|
Object Detection (Q)
|
93% |
9737
777.0 IPS |
|
Face Detection (SP)
|
100% |
2196
26.1 IPS |
|
Face Detection (HP)
|
100% |
12613
149.9 IPS |
|
Face Detection (Q)
|
100% |
14833
176.2 IPS |
|
Depth Estimation (SP)
|
100% |
3962
30.5 IPS |
|
Depth Estimation (HP)
|
99% |
60588
466.8 IPS |
|
Depth Estimation (Q)
|
97% |
63672
492.3 IPS |
|
Style Transfer (SP)
|
100% |
15728
20.2 IPS |
|
Style Transfer (HP)
|
100% |
148704
191.2 IPS |
|
Style Transfer (Q)
|
100% |
149673
192.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2928
108.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
20097
742.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
24858
921.0 IPS |
|
Text Classification (SP)
|
100% |
712
950.0 IPS |
|
Text Classification (HP)
|
100% |
906
1.21 KIPS |
|
Text Classification (Q)
|
93% |
812
1.09 KIPS |
|
Machine Translation (SP)
|
100% |
1994
34.4 IPS |
|
Machine Translation (HP)
|
96% |
2248
38.9 IPS |
|
Machine Translation (Q)
|
98% |
2240
38.7 IPS |