User | igormp |
Upload Date | August 21 2024 03:04 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
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% |
1148
213.5 IPS |
|
Image Classification (HP)
|
100% |
7484
1.39 KIPS |
|
Image Classification (Q)
|
99% |
7368
1.37 KIPS |
|
Image Segmentation (SP)
|
100% |
803
13.0 IPS |
|
Image Segmentation (HP)
|
100% |
6395
103.7 IPS |
|
Image Segmentation (Q)
|
100% |
6445
104.5 IPS |
|
Pose Estimation (SP)
|
100% |
15469
18.0 IPS |
|
Pose Estimation (HP)
|
100% |
103308
120.5 IPS |
|
Pose Estimation (Q)
|
94% |
98710
115.8 IPS |
|
Object Detection (SP)
|
100% |
1243
98.6 IPS |
|
Object Detection (HP)
|
100% |
9730
771.8 IPS |
|
Object Detection (Q)
|
93% |
9577
764.1 IPS |
|
Face Detection (SP)
|
100% |
2185
26.0 IPS |
|
Face Detection (HP)
|
100% |
12492
148.4 IPS |
|
Face Detection (Q)
|
100% |
14776
175.6 IPS |
|
Depth Estimation (SP)
|
100% |
4546
35.0 IPS |
|
Depth Estimation (HP)
|
99% |
59794
460.7 IPS |
|
Depth Estimation (Q)
|
97% |
61706
477.1 IPS |
|
Style Transfer (SP)
|
100% |
15629
20.1 IPS |
|
Style Transfer (HP)
|
100% |
150004
192.8 IPS |
|
Style Transfer (Q)
|
100% |
148711
191.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3632
134.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
19323
713.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
23275
862.3 IPS |
|
Text Classification (SP)
|
100% |
1038
1.39 KIPS |
|
Text Classification (HP)
|
100% |
882
1.18 KIPS |
|
Text Classification (Q)
|
93% |
808
1.08 KIPS |
|
Machine Translation (SP)
|
100% |
2184
37.6 IPS |
|
Machine Translation (HP)
|
96% |
2222
38.4 IPS |
|
Machine Translation (Q)
|
98% |
2179
37.7 IPS |