User | i_am_taikun |
Upload Date | March 08 2025 06:25 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
8036
1.49 KIPS |
|
Image Classification (HP)
|
100% |
8757
1.63 KIPS |
|
Image Classification (Q)
|
97% |
7118
1.33 KIPS |
|
Image Segmentation (SP)
|
100% |
12361
200.4 IPS |
|
Image Segmentation (HP)
|
100% |
13280
215.3 IPS |
|
Image Segmentation (Q)
|
99% |
13529
219.3 IPS |
|
Pose Estimation (SP)
|
100% |
56899
66.4 IPS |
|
Pose Estimation (HP)
|
100% |
59287
69.2 IPS |
|
Pose Estimation (Q)
|
95% |
56052
65.7 IPS |
|
Object Detection (SP)
|
100% |
7396
586.7 IPS |
|
Object Detection (HP)
|
100% |
7916
627.9 IPS |
|
Object Detection (Q)
|
91% |
6692
534.7 IPS |
|
Face Detection (SP)
|
100% |
25678
305.1 IPS |
|
Face Detection (HP)
|
100% |
29046
345.1 IPS |
|
Face Detection (Q)
|
100% |
21116
250.9 IPS |
|
Depth Estimation (SP)
|
100% |
34446
265.4 IPS |
|
Depth Estimation (HP)
|
99% |
36432
280.7 IPS |
|
Depth Estimation (Q)
|
85% |
30819
240.9 IPS |
|
Style Transfer (SP)
|
100% |
125894
161.8 IPS |
|
Style Transfer (HP)
|
100% |
138114
177.5 IPS |
|
Style Transfer (Q)
|
96% |
129835
167.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
23822
879.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
25431
939.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
20171
744.8 IPS |
|
Text Classification (SP)
|
100% |
2933
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5219
6.97 KIPS |
|
Text Classification (Q)
|
93% |
5207
6.99 KIPS |
|
Machine Translation (SP)
|
100% |
1516
26.1 IPS |
|
Machine Translation (HP)
|
100% |
2631
45.3 IPS |
|
Machine Translation (Q)
|
98% |
2665
46.1 IPS |