NN filter for Very Low Operational Point (VLOP), targeting complexity of 5kMAC/pixel level, was proposed in JVET-AH0051 and adopted to NNVC. This contribution reports the results of EE1-1.5, which adapt the LOP3 architecture (17kMAC/pixel) to VLOP. Complexity reduction was achieved by adjusting the numbers of channels and backbone blocks. The proposed VLOP model has a reported complexity of 5.16 kMAC/pixel and 60.7k parameters. Stage 3 training of the proposed model over LOP dataset was performed independently by its proponents. The performance of the int16 model (including NNIntra) compared to the NNVC-9.1 VLOP (NNIntra+VLOP) is reported below: