Upload Date | November 19 2024 08:07 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1515
281.8 IPS |
|
Image Classification (HP)
|
100% |
16130
3.00 KIPS |
|
Image Classification (Q)
|
97% |
16994
3.17 KIPS |
|
Image Segmentation (SP)
|
100% |
1846
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
21427
347.3 IPS |
|
Image Segmentation (Q)
|
99% |
27017
438.0 IPS |
|
Pose Estimation (SP)
|
100% |
16781
19.6 IPS |
|
Pose Estimation (HP)
|
100% |
120342
140.4 IPS |
|
Pose Estimation (Q)
|
95% |
118662
139.1 IPS |
|
Object Detection (SP)
|
100% |
1990
157.8 IPS |
|
Object Detection (HP)
|
100% |
16594
1.32 KIPS |
|
Object Detection (Q)
|
91% |
16604
1.33 KIPS |
|
Face Detection (SP)
|
100% |
4094
48.6 IPS |
|
Face Detection (HP)
|
100% |
38385
456.1 IPS |
|
Face Detection (Q)
|
100% |
50335
598.1 IPS |
|
Depth Estimation (SP)
|
100% |
7507
57.8 IPS |
|
Depth Estimation (HP)
|
99% |
100963
777.9 IPS |
|
Depth Estimation (Q)
|
85% |
115230
900.9 IPS |
|
Style Transfer (SP)
|
100% |
31203
40.1 IPS |
|
Style Transfer (HP)
|
100% |
216106
277.8 IPS |
|
Style Transfer (Q)
|
96% |
210595
271.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5773
213.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
38800
1.43 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50626
1.87 KIPS |
|
Text Classification (SP)
|
100% |
2710
3.62 KIPS |
|
Text Classification (HP)
|
100% |
4691
6.26 KIPS |
|
Text Classification (Q)
|
93% |
4667
6.26 KIPS |
|
Machine Translation (SP)
|
100% |
5051
87.0 IPS |
|
Machine Translation (HP)
|
100% |
7302
125.8 IPS |
|
Machine Translation (Q)
|
98% |
8180
141.4 IPS |