User | GPV67 |
Upload Date | December 04 2024 12:59 AM |
Views | 2 |
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% |
2077
386.3 IPS |
|
Image Classification (HP)
|
100% |
18445
3.43 KIPS |
|
Image Classification (Q)
|
97% |
22888
4.27 KIPS |
|
Image Segmentation (SP)
|
100% |
2441
39.6 IPS |
|
Image Segmentation (HP)
|
100% |
23311
377.9 IPS |
|
Image Segmentation (Q)
|
99% |
32556
527.8 IPS |
|
Pose Estimation (SP)
|
100% |
18877
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123474
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
231863
271.8 IPS |
|
Object Detection (SP)
|
100% |
2477
196.5 IPS |
|
Object Detection (HP)
|
100% |
20632
1.64 KIPS |
|
Object Detection (Q)
|
91% |
24660
1.97 KIPS |
|
Face Detection (SP)
|
100% |
4558
54.2 IPS |
|
Face Detection (HP)
|
100% |
44936
533.9 IPS |
|
Face Detection (Q)
|
100% |
64754
769.4 IPS |
|
Depth Estimation (SP)
|
100% |
8837
68.1 IPS |
|
Depth Estimation (HP)
|
99% |
108516
836.1 IPS |
|
Depth Estimation (Q)
|
85% |
182605
1.43 KIPS |
|
Style Transfer (SP)
|
100% |
36146
46.5 IPS |
|
Style Transfer (HP)
|
100% |
237939
305.9 IPS |
|
Style Transfer (Q)
|
96% |
304705
393.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7084
261.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
48083
1.78 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80772
2.98 KIPS |
|
Text Classification (SP)
|
100% |
2967
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5773
7.71 KIPS |
|
Text Classification (Q)
|
93% |
5743
7.71 KIPS |
|
Machine Translation (SP)
|
100% |
5705
98.3 IPS |
|
Machine Translation (HP)
|
100% |
16632
286.5 IPS |
|
Machine Translation (Q)
|
98% |
17208
297.4 IPS |