User | mikenicolai |
Upload Date | September 03 2024 05:17 AM |
Views | 19 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,10 |
Motherboard | Mac15,10 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1159
215.6 IPS |
|
Image Classification (HP)
|
100% |
6817
1.27 KIPS |
|
Image Classification (Q)
|
99% |
7265
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
843
13.7 IPS |
|
Image Segmentation (HP)
|
100% |
6393
103.6 IPS |
|
Image Segmentation (Q)
|
100% |
6419
104.1 IPS |
|
Pose Estimation (SP)
|
100% |
14890
17.4 IPS |
|
Pose Estimation (HP)
|
100% |
102787
119.9 IPS |
|
Pose Estimation (Q)
|
94% |
98627
115.7 IPS |
|
Object Detection (SP)
|
100% |
1277
101.3 IPS |
|
Object Detection (HP)
|
100% |
9403
745.8 IPS |
|
Object Detection (Q)
|
93% |
9453
754.3 IPS |
|
Face Detection (SP)
|
100% |
2251
26.7 IPS |
|
Face Detection (HP)
|
100% |
12550
149.1 IPS |
|
Face Detection (Q)
|
100% |
14809
176.0 IPS |
|
Depth Estimation (SP)
|
100% |
3880
29.9 IPS |
|
Depth Estimation (HP)
|
99% |
59055
455.0 IPS |
|
Depth Estimation (Q)
|
97% |
61181
473.1 IPS |
|
Style Transfer (SP)
|
100% |
15657
20.1 IPS |
|
Style Transfer (HP)
|
100% |
149356
192.0 IPS |
|
Style Transfer (Q)
|
100% |
149469
192.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2536
93.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
19099
705.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
23166
858.3 IPS |
|
Text Classification (SP)
|
100% |
675
901.0 IPS |
|
Text Classification (HP)
|
100% |
901
1.20 KIPS |
|
Text Classification (Q)
|
93% |
778
1.04 KIPS |
|
Machine Translation (SP)
|
100% |
1933
33.3 IPS |
|
Machine Translation (HP)
|
96% |
2246
38.8 IPS |
|
Machine Translation (Q)
|
98% |
2202
38.1 IPS |