User | mamiyoshi |
Upload Date | November 09 2024 01:35 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1513
281.4 IPS |
|
Image Classification (HP)
|
100% |
16309
3.03 KIPS |
|
Image Classification (Q)
|
97% |
17677
3.30 KIPS |
|
Image Segmentation (SP)
|
100% |
1926
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
22043
357.3 IPS |
|
Image Segmentation (Q)
|
99% |
27038
438.3 IPS |
|
Pose Estimation (SP)
|
100% |
16763
19.6 IPS |
|
Pose Estimation (HP)
|
100% |
121546
141.8 IPS |
|
Pose Estimation (Q)
|
95% |
118843
139.3 IPS |
|
Object Detection (SP)
|
100% |
1984
157.4 IPS |
|
Object Detection (HP)
|
100% |
16837
1.34 KIPS |
|
Object Detection (Q)
|
91% |
17211
1.38 KIPS |
|
Face Detection (SP)
|
100% |
4074
48.4 IPS |
|
Face Detection (HP)
|
100% |
37994
451.5 IPS |
|
Face Detection (Q)
|
100% |
49022
582.5 IPS |
|
Depth Estimation (SP)
|
100% |
7314
56.4 IPS |
|
Depth Estimation (HP)
|
99% |
101199
779.7 IPS |
|
Depth Estimation (Q)
|
85% |
116351
909.7 IPS |
|
Style Transfer (SP)
|
100% |
30993
39.8 IPS |
|
Style Transfer (HP)
|
100% |
216666
278.5 IPS |
|
Style Transfer (Q)
|
96% |
210637
271.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5895
217.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
38328
1.42 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50821
1.88 KIPS |
|
Text Classification (SP)
|
100% |
2747
3.67 KIPS |
|
Text Classification (HP)
|
100% |
4845
6.47 KIPS |
|
Text Classification (Q)
|
93% |
5018
6.73 KIPS |
|
Machine Translation (SP)
|
100% |
4945
85.2 IPS |
|
Machine Translation (HP)
|
100% |
4959
85.4 IPS |
|
Machine Translation (Q)
|
98% |
4846
83.7 IPS |