User | RG22032 |
Upload Date | January 28 2025 02:16 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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% |
2091
388.9 IPS |
|
Image Classification (HP)
|
100% |
17937
3.34 KIPS |
|
Image Classification (Q)
|
97% |
23723
4.43 KIPS |
|
Image Segmentation (SP)
|
100% |
2501
40.5 IPS |
|
Image Segmentation (HP)
|
100% |
23105
374.5 IPS |
|
Image Segmentation (Q)
|
99% |
32059
519.7 IPS |
|
Pose Estimation (SP)
|
100% |
19009
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123058
143.6 IPS |
|
Pose Estimation (Q)
|
95% |
230002
269.6 IPS |
|
Object Detection (SP)
|
100% |
2466
195.6 IPS |
|
Object Detection (HP)
|
100% |
20183
1.60 KIPS |
|
Object Detection (Q)
|
91% |
24022
1.92 KIPS |
|
Face Detection (SP)
|
100% |
4464
53.0 IPS |
|
Face Detection (HP)
|
100% |
43795
520.4 IPS |
|
Face Detection (Q)
|
100% |
62987
748.4 IPS |
|
Depth Estimation (SP)
|
100% |
8593
66.2 IPS |
|
Depth Estimation (HP)
|
99% |
106181
818.1 IPS |
|
Depth Estimation (Q)
|
85% |
176331
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35729
45.9 IPS |
|
Style Transfer (HP)
|
100% |
236840
304.5 IPS |
|
Style Transfer (Q)
|
96% |
301390
388.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
7049
260.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
46700
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78064
2.88 KIPS |
|
Text Classification (SP)
|
100% |
2961
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5675
7.57 KIPS |
|
Text Classification (Q)
|
93% |
6430
8.63 KIPS |
|
Machine Translation (SP)
|
100% |
5673
97.7 IPS |
|
Machine Translation (HP)
|
100% |
16426
283.0 IPS |
|
Machine Translation (Q)
|
98% |
16726
289.0 IPS |