Multinomial logit model and weights

I'm using multinomial logit model in order to model whether a household owns, has access to a computer or none. Household data is weighted - it has a variable which indicates the number of households in the population represented by the household in the sample. Should I use this weights in the analysis? The data is in the long format. I'm using R studio and want to se what socioeconomic factors are contributing to different adoption type of a computer (owned, access, none) by a household.

Any guidelines will be much appreciated by a confused beginner.