User | elnoyo |
Upload Date | December 03 2024 01:13 PM |
Views | 9 |
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, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2074
385.7 IPS |
|
Image Classification (HP)
|
100% |
17617
3.28 KIPS |
|
Image Classification (Q)
|
97% |
22700
4.24 KIPS |
|
Image Segmentation (SP)
|
100% |
2521
40.9 IPS |
|
Image Segmentation (HP)
|
100% |
23210
376.2 IPS |
|
Image Segmentation (Q)
|
99% |
32413
525.4 IPS |
|
Pose Estimation (SP)
|
100% |
18969
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
124677
145.5 IPS |
|
Pose Estimation (Q)
|
95% |
232099
272.0 IPS |
|
Object Detection (SP)
|
100% |
2489
197.4 IPS |
|
Object Detection (HP)
|
100% |
19718
1.56 KIPS |
|
Object Detection (Q)
|
91% |
24689
1.97 KIPS |
|
Face Detection (SP)
|
100% |
4562
54.2 IPS |
|
Face Detection (HP)
|
100% |
44787
532.2 IPS |
|
Face Detection (Q)
|
100% |
64582
767.4 IPS |
|
Depth Estimation (SP)
|
100% |
8895
68.5 IPS |
|
Depth Estimation (HP)
|
99% |
106120
817.6 IPS |
|
Depth Estimation (Q)
|
85% |
181401
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
35028
45.0 IPS |
|
Style Transfer (HP)
|
100% |
238891
307.1 IPS |
|
Style Transfer (Q)
|
96% |
302082
389.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7030
259.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
46908
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78847
2.91 KIPS |
|
Text Classification (SP)
|
100% |
2934
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5085
6.79 KIPS |
|
Text Classification (Q)
|
93% |
5726
7.69 KIPS |
|
Machine Translation (SP)
|
100% |
5807
100.0 IPS |
|
Machine Translation (HP)
|
100% |
16287
280.5 IPS |
|
Machine Translation (Q)
|
98% |
16384
283.1 IPS |