User | kolored |
Upload Date | September 03 2024 04:43 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5813
1.08 KIPS |
|
Image Classification (HP)
|
100% |
5907
1.10 KIPS |
|
Image Classification (Q)
|
99% |
5317
991.6 IPS |
|
Image Segmentation (SP)
|
100% |
10859
176.0 IPS |
|
Image Segmentation (HP)
|
100% |
10505
170.3 IPS |
|
Image Segmentation (Q)
|
100% |
10085
163.5 IPS |
|
Pose Estimation (SP)
|
100% |
60729
70.9 IPS |
|
Pose Estimation (HP)
|
100% |
63535
74.1 IPS |
|
Pose Estimation (Q)
|
96% |
56148
65.8 IPS |
|
Object Detection (SP)
|
100% |
5541
439.5 IPS |
|
Object Detection (HP)
|
100% |
5888
467.0 IPS |
|
Object Detection (Q)
|
92% |
4884
389.8 IPS |
|
Face Detection (SP)
|
100% |
21634
257.1 IPS |
|
Face Detection (HP)
|
100% |
20172
239.7 IPS |
|
Face Detection (Q)
|
100% |
15634
185.8 IPS |
|
Depth Estimation (SP)
|
100% |
28248
217.6 IPS |
|
Depth Estimation (HP)
|
99% |
28975
223.2 IPS |
|
Depth Estimation (Q)
|
97% |
28547
220.7 IPS |
|
Style Transfer (SP)
|
100% |
112122
144.1 IPS |
|
Style Transfer (HP)
|
100% |
125644
161.5 IPS |
|
Style Transfer (Q)
|
100% |
123820
159.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
19886
734.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
20476
756.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
15441
572.1 IPS |
|
Text Classification (SP)
|
100% |
341
454.7 IPS |
|
Text Classification (HP)
|
100% |
494
658.7 IPS |
|
Text Classification (Q)
|
93% |
492
660.8 IPS |
|
Machine Translation (SP)
|
100% |
1122
19.3 IPS |
|
Machine Translation (HP)
|
100% |
1188
20.5 IPS |
|
Machine Translation (Q)
|
98% |
1234
21.3 IPS |