User | t0m3k |
Upload Date | December 29 2024 02:19 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D5034f) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,4 |
Motherboard | MacBookPro18,4 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4326
804.5 IPS |
|
Image Classification (HP)
|
100% |
4518
840.2 IPS |
|
Image Classification (Q)
|
97% |
3679
686.6 IPS |
|
Image Segmentation (SP)
|
100% |
8625
139.8 IPS |
|
Image Segmentation (HP)
|
100% |
8492
137.7 IPS |
|
Image Segmentation (Q)
|
99% |
8616
139.7 IPS |
|
Pose Estimation (SP)
|
100% |
47173
55.0 IPS |
|
Pose Estimation (HP)
|
100% |
49272
57.5 IPS |
|
Pose Estimation (Q)
|
95% |
45495
53.3 IPS |
|
Object Detection (SP)
|
100% |
4581
363.4 IPS |
|
Object Detection (HP)
|
100% |
4818
382.2 IPS |
|
Object Detection (Q)
|
91% |
4063
324.7 IPS |
|
Face Detection (SP)
|
100% |
18043
214.4 IPS |
|
Face Detection (HP)
|
100% |
18545
220.4 IPS |
|
Face Detection (Q)
|
100% |
13393
159.1 IPS |
|
Depth Estimation (SP)
|
100% |
23365
180.0 IPS |
|
Depth Estimation (HP)
|
99% |
23894
184.1 IPS |
|
Depth Estimation (Q)
|
85% |
20266
158.4 IPS |
|
Style Transfer (SP)
|
100% |
79702
102.5 IPS |
|
Style Transfer (HP)
|
100% |
94410
121.4 IPS |
|
Style Transfer (Q)
|
96% |
88699
114.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
15414
569.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
15591
575.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
12251
452.4 IPS |
|
Text Classification (SP)
|
100% |
2243
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3767
5.03 KIPS |
|
Text Classification (Q)
|
93% |
3755
5.04 KIPS |
|
Machine Translation (SP)
|
100% |
1011
17.4 IPS |
|
Machine Translation (HP)
|
100% |
1023
17.6 IPS |
|
Machine Translation (Q)
|
98% |
1050
18.2 IPS |