Upload Date | November 21 2024 12:34 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,7 |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7530
1.40 KIPS |
|
Image Classification (HP)
|
100% |
7965
1.48 KIPS |
|
Image Classification (Q)
|
97% |
6855
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
11979
194.2 IPS |
|
Image Segmentation (HP)
|
100% |
12916
209.4 IPS |
|
Image Segmentation (Q)
|
99% |
13234
214.5 IPS |
|
Pose Estimation (SP)
|
100% |
56681
66.1 IPS |
|
Pose Estimation (HP)
|
100% |
59055
68.9 IPS |
|
Pose Estimation (Q)
|
95% |
55869
65.5 IPS |
|
Object Detection (SP)
|
100% |
7141
566.4 IPS |
|
Object Detection (HP)
|
100% |
7684
609.5 IPS |
|
Object Detection (Q)
|
91% |
6422
513.1 IPS |
|
Face Detection (SP)
|
100% |
25432
302.2 IPS |
|
Face Detection (HP)
|
100% |
27324
324.7 IPS |
|
Face Detection (Q)
|
100% |
20739
246.4 IPS |
|
Depth Estimation (SP)
|
100% |
33757
260.1 IPS |
|
Depth Estimation (HP)
|
99% |
35696
275.0 IPS |
|
Depth Estimation (Q)
|
85% |
29049
227.0 IPS |
|
Style Transfer (SP)
|
100% |
123798
159.1 IPS |
|
Style Transfer (HP)
|
100% |
134624
173.1 IPS |
|
Style Transfer (Q)
|
96% |
127159
164.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
22749
840.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
24022
887.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
19151
707.2 IPS |
|
Text Classification (SP)
|
100% |
2945
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5173
6.90 KIPS |
|
Text Classification (Q)
|
93% |
5162
6.93 KIPS |
|
Machine Translation (SP)
|
100% |
2795
48.1 IPS |
|
Machine Translation (HP)
|
100% |
2780
47.9 IPS |
|
Machine Translation (Q)
|
98% |
2293
39.6 IPS |