User | Tycho |
Upload Date | August 21 2024 10:31 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,8 |
Motherboard | Mac15,8 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7588
1.41 KIPS |
|
Image Classification (HP)
|
100% |
7900
1.47 KIPS |
|
Image Classification (Q)
|
99% |
7196
1.34 KIPS |
|
Image Segmentation (SP)
|
100% |
16781
272.0 IPS |
|
Image Segmentation (HP)
|
100% |
17628
285.8 IPS |
|
Image Segmentation (Q)
|
100% |
17119
277.5 IPS |
|
Pose Estimation (SP)
|
100% |
91753
107.1 IPS |
|
Pose Estimation (HP)
|
100% |
95165
111.0 IPS |
|
Pose Estimation (Q)
|
97% |
83491
97.8 IPS |
|
Object Detection (SP)
|
100% |
7629
605.2 IPS |
|
Object Detection (HP)
|
100% |
8206
650.9 IPS |
|
Object Detection (Q)
|
91% |
6898
551.2 IPS |
|
Face Detection (SP)
|
100% |
32056
380.9 IPS |
|
Face Detection (HP)
|
100% |
36459
433.2 IPS |
|
Face Detection (Q)
|
100% |
25376
301.5 IPS |
|
Depth Estimation (SP)
|
100% |
37895
292.0 IPS |
|
Depth Estimation (HP)
|
99% |
40708
313.6 IPS |
|
Depth Estimation (Q)
|
97% |
6108
47.2 IPS |
|
Style Transfer (SP)
|
100% |
186329
239.5 IPS |
|
Style Transfer (HP)
|
100% |
204732
263.2 IPS |
|
Style Transfer (Q)
|
100% |
196428
252.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
24127
890.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25662
947.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
18665
691.5 IPS |
|
Text Classification (SP)
|
100% |
2731
3.65 KIPS |
|
Text Classification (HP)
|
100% |
4880
6.51 KIPS |
|
Text Classification (Q)
|
93% |
4699
6.31 KIPS |
|
Machine Translation (SP)
|
100% |
1957
33.7 IPS |
|
Machine Translation (HP)
|
100% |
2053
35.4 IPS |
|
Machine Translation (Q)
|
98% |
2502
43.2 IPS |