The purpose of this paper is to investigate empirically the main determinants of patenting behaviour from small- to medium-sized firms in least-developed countries (LDCs). Probit modelling is proposed and tested using data collected from the World Bank Investment Climate Survey (ICS) for 7 LDCs (Algeria, Kazakhstan, Nigeria, Ecuador, Colombia, Mexico, and Chile). Putting at the core of the explanations the type of innovation carried out, our findings show that there is not a huge gap with what the literature considers to be important for developed countries: radical inventor patents more than an incremental innovator; a product innovator is more prone to patent than a process innovator. In line with the recent literature, a complex innovator in general patents more than a single one (the case of medium firms sets up an exception). We find there is a size effect as well. These results have a direct implication on firm innovation strategy and more generally on public policy intervention to deepen the appropriation returns of innovation and to increase the use of patent by small firms. Prior studies have under-investigated this topic in developing economies. This research aims to fill this gap.