User | edwardhchan |
Upload Date | January 16 2025 08:22 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1589
295.4 IPS |
|
Image Classification (HP)
|
100% |
16912
3.15 KIPS |
|
Image Classification (Q)
|
97% |
18959
3.54 KIPS |
|
Image Segmentation (SP)
|
100% |
1912
31.0 IPS |
|
Image Segmentation (HP)
|
100% |
21741
352.4 IPS |
|
Image Segmentation (Q)
|
99% |
27217
441.2 IPS |
|
Pose Estimation (SP)
|
100% |
8956
10.5 IPS |
|
Pose Estimation (HP)
|
100% |
121493
141.8 IPS |
|
Pose Estimation (Q)
|
95% |
120633
141.4 IPS |
|
Object Detection (SP)
|
100% |
1847
146.5 IPS |
|
Object Detection (HP)
|
100% |
17411
1.38 KIPS |
|
Object Detection (Q)
|
91% |
19816
1.58 KIPS |
|
Face Detection (SP)
|
100% |
3746
44.5 IPS |
|
Face Detection (HP)
|
100% |
39168
465.4 IPS |
|
Face Detection (Q)
|
100% |
51233
608.8 IPS |
|
Depth Estimation (SP)
|
100% |
7212
55.6 IPS |
|
Depth Estimation (HP)
|
99% |
98109
755.9 IPS |
|
Depth Estimation (Q)
|
85% |
122154
955.1 IPS |
|
Style Transfer (SP)
|
100% |
22415
28.8 IPS |
|
Style Transfer (HP)
|
100% |
225710
290.2 IPS |
|
Style Transfer (Q)
|
96% |
222116
286.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5288
195.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
44527
1.64 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58421
2.16 KIPS |
|
Text Classification (SP)
|
100% |
2848
3.80 KIPS |
|
Text Classification (HP)
|
100% |
5018
6.70 KIPS |
|
Text Classification (Q)
|
93% |
4835
6.49 KIPS |
|
Machine Translation (SP)
|
100% |
3564
61.4 IPS |
|
Machine Translation (HP)
|
100% |
4595
79.2 IPS |
|
Machine Translation (Q)
|
98% |
4722
81.6 IPS |