User | Coin1news |
Upload Date | December 10 2024 07:45 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2075
385.9 IPS |
|
Image Classification (HP)
|
100% |
17540
3.26 KIPS |
|
Image Classification (Q)
|
97% |
22399
4.18 KIPS |
|
Image Segmentation (SP)
|
100% |
2457
39.8 IPS |
|
Image Segmentation (HP)
|
100% |
23168
375.6 IPS |
|
Image Segmentation (Q)
|
99% |
32071
519.9 IPS |
|
Pose Estimation (SP)
|
100% |
18834
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123503
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
232147
272.1 IPS |
|
Object Detection (SP)
|
100% |
2490
197.5 IPS |
|
Object Detection (HP)
|
100% |
19841
1.57 KIPS |
|
Object Detection (Q)
|
91% |
24446
1.95 KIPS |
|
Face Detection (SP)
|
100% |
4612
54.8 IPS |
|
Face Detection (HP)
|
100% |
44707
531.2 IPS |
|
Face Detection (Q)
|
100% |
64519
766.6 IPS |
|
Depth Estimation (SP)
|
100% |
8909
68.6 IPS |
|
Depth Estimation (HP)
|
99% |
111514
859.1 IPS |
|
Depth Estimation (Q)
|
85% |
177722
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
36140
46.5 IPS |
|
Style Transfer (HP)
|
100% |
239408
307.8 IPS |
|
Style Transfer (Q)
|
96% |
303872
392.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
7007
258.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
46499
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77862
2.88 KIPS |
|
Text Classification (SP)
|
100% |
2927
3.91 KIPS |
|
Text Classification (HP)
|
100% |
4855
6.48 KIPS |
|
Text Classification (Q)
|
93% |
4935
6.62 KIPS |
|
Machine Translation (SP)
|
100% |
5693
98.1 IPS |
|
Machine Translation (HP)
|
100% |
16350
281.6 IPS |
|
Machine Translation (Q)
|
98% |
16350
282.5 IPS |