User | marsplaneetta |
Upload Date | August 15 2024 11:10 PM |
Views | 7 |
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 (16-inch, Nov 2023) |
Model ID | Mac15,11 |
Motherboard | Mac15,11 |
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% |
1134
210.9 IPS |
|
Image Classification (HP)
|
100% |
6719
1.25 KIPS |
|
Image Classification (Q)
|
99% |
6872
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
834
13.5 IPS |
|
Image Segmentation (HP)
|
100% |
6397
103.7 IPS |
|
Image Segmentation (Q)
|
100% |
6408
103.9 IPS |
|
Pose Estimation (SP)
|
100% |
15499
18.1 IPS |
|
Pose Estimation (HP)
|
100% |
103032
120.2 IPS |
|
Pose Estimation (Q)
|
94% |
98642
115.7 IPS |
|
Object Detection (SP)
|
100% |
1243
98.6 IPS |
|
Object Detection (HP)
|
100% |
9450
749.6 IPS |
|
Object Detection (Q)
|
93% |
9490
757.2 IPS |
|
Face Detection (SP)
|
100% |
2319
27.6 IPS |
|
Face Detection (HP)
|
100% |
12755
151.6 IPS |
|
Face Detection (Q)
|
100% |
14643
174.0 IPS |
|
Depth Estimation (SP)
|
100% |
4172
32.1 IPS |
|
Depth Estimation (HP)
|
99% |
59527
458.6 IPS |
|
Depth Estimation (Q)
|
97% |
61544
475.9 IPS |
|
Style Transfer (SP)
|
100% |
15589
20.0 IPS |
|
Style Transfer (HP)
|
100% |
149637
192.4 IPS |
|
Style Transfer (Q)
|
100% |
149205
191.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3362
124.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
19296
712.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
24385
903.4 IPS |
|
Text Classification (SP)
|
100% |
577
770.4 IPS |
|
Text Classification (HP)
|
100% |
690
921.0 IPS |
|
Text Classification (Q)
|
93% |
872
1.17 KIPS |
|
Machine Translation (SP)
|
100% |
1839
31.7 IPS |
|
Machine Translation (HP)
|
96% |
2207
38.2 IPS |
|
Machine Translation (Q)
|
98% |
2237
38.7 IPS |