Solid modelling in mineral resource estimation is an important phase since block model is built with respected to the ore-body. If the solid model of the ore deposit is not consistent with approximate real case, error will accumulate progressively through the estimation steps. One of the major mistakes would be the presence of the estimated blocks where there is no ore-body extension. Interpretation in classical approach, where sections are taken through drill-holes and polygonized with geological and mining knowledge, is very critical and the process is always time consuming. In this study, support vector machine (SVM) algorithm compiled by authors is offered as a solution for 3D solid modelling. The proposed implicit method is based on Gaussian radial basis functions and it is applied to an epithermal gold deposit in order to build 3D solid model of the mineralization. The input variables are converted to indicator values which are ore-zone and no-ore-zone. Mineralized zones in each section is classified with SVM based on indicator variables of drill-holes falling in corresponding sections and finally these sections are combined in order to create 3D solid model. The SVM is fast when compared to the classical slice sectioning and 3D solid model reveals consistent result. It is crucial that these results should not be regarded as finalized solid. It has to be checked and re-organized if necessary in light of geological and mining knowledge.