User | teotwawk |
Upload Date | April 22 2025 08:52 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 14.6 (Build 23G80) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1266
235.3 IPS |
|
Image Classification (HP)
|
100% |
7482
1.39 KIPS |
|
Image Classification (Q)
|
97% |
7847
1.46 KIPS |
|
Image Segmentation (SP)
|
100% |
887
14.4 IPS |
|
Image Segmentation (HP)
|
100% |
6694
108.5 IPS |
|
Image Segmentation (Q)
|
99% |
13011
210.9 IPS |
|
Pose Estimation (SP)
|
100% |
8499
9.92 IPS |
|
Pose Estimation (HP)
|
100% |
102997
120.2 IPS |
|
Pose Estimation (Q)
|
95% |
104294
122.2 IPS |
|
Object Detection (SP)
|
100% |
1500
119.0 IPS |
|
Object Detection (HP)
|
100% |
9984
792.0 IPS |
|
Object Detection (Q)
|
93% |
10569
843.3 IPS |
|
Face Detection (SP)
|
100% |
2432
28.9 IPS |
|
Face Detection (HP)
|
100% |
13468
160.0 IPS |
|
Face Detection (Q)
|
100% |
15245
181.1 IPS |
|
Depth Estimation (SP)
|
100% |
4787
36.9 IPS |
|
Depth Estimation (HP)
|
99% |
58655
451.9 IPS |
|
Depth Estimation (Q)
|
85% |
70982
555.0 IPS |
|
Style Transfer (SP)
|
100% |
12496
16.1 IPS |
|
Style Transfer (HP)
|
100% |
152152
195.6 IPS |
|
Style Transfer (Q)
|
96% |
142111
183.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4053
149.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
20960
773.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
27125
1.00 KIPS |
|
Text Classification (SP)
|
100% |
748
998.5 IPS |
|
Text Classification (HP)
|
100% |
4641
6.19 KIPS |
|
Text Classification (Q)
|
93% |
4556
6.11 KIPS |
|
Machine Translation (SP)
|
100% |
2199
37.9 IPS |
|
Machine Translation (HP)
|
100% |
2911
50.1 IPS |
|
Machine Translation (Q)
|
98% |
2926
50.6 IPS |