User | tensojka |
Upload Date | January 28 2025 08:30 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7456
1.39 KIPS |
|
Image Classification (HP)
|
100% |
7893
1.47 KIPS |
|
Image Classification (Q)
|
97% |
6854
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
11856
192.2 IPS |
|
Image Segmentation (HP)
|
100% |
12785
207.3 IPS |
|
Image Segmentation (Q)
|
99% |
13217
214.2 IPS |
|
Pose Estimation (SP)
|
100% |
56411
65.8 IPS |
|
Pose Estimation (HP)
|
100% |
58930
68.8 IPS |
|
Pose Estimation (Q)
|
95% |
55859
65.5 IPS |
|
Object Detection (SP)
|
100% |
7124
565.1 IPS |
|
Object Detection (HP)
|
100% |
7597
602.6 IPS |
|
Object Detection (Q)
|
91% |
6334
506.1 IPS |
|
Face Detection (SP)
|
100% |
25086
298.1 IPS |
|
Face Detection (HP)
|
100% |
28004
332.7 IPS |
|
Face Detection (Q)
|
100% |
21053
250.2 IPS |
|
Depth Estimation (SP)
|
100% |
33054
254.7 IPS |
|
Depth Estimation (HP)
|
99% |
35479
273.3 IPS |
|
Depth Estimation (Q)
|
85% |
29700
232.1 IPS |
|
Style Transfer (SP)
|
100% |
123140
158.3 IPS |
|
Style Transfer (HP)
|
100% |
134681
173.1 IPS |
|
Style Transfer (Q)
|
96% |
127019
163.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
22461
829.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
24531
905.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
18999
701.5 IPS |
|
Text Classification (SP)
|
100% |
2929
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5197
6.94 KIPS |
|
Text Classification (Q)
|
93% |
5130
6.89 KIPS |
|
Machine Translation (SP)
|
100% |
2246
38.7 IPS |
|
Machine Translation (HP)
|
100% |
1479
25.5 IPS |
|
Machine Translation (Q)
|
98% |
1549
26.8 IPS |