W e propose using a Gaussian Mixture Model (GMM) as reverse tr ansition operator (kernel) within the Denoising Diffusion Implicit Model s (DDIM) framework, which is one of the most widely used approaches for accelerat ed sampling from pre-trained Denoising Diffusion Probabilistic Models (DD PM). Specifically we match the first and second order central moments of the DDPM fo rward marginals by constraining the parameters of the GMM. W e see that moment matching is sufficient to obtain samples with equal or better quality than th e original DDIM with Gaussian kernels. W e provide experimental results with unc onditional models trained on CelebAHQ and FFHQ and class-conditional models t rained on ImageNet datasets respectively. Our results suggest that usin g the GMM kernel leads to significant improvements in the quality of the generated s amples when the number of sampling steps is small, as measured by FID and IS metri cs. For example on ImageNet 256x256, using 10 sampling steps, we achieve a FI D of 6.94 and IS of 207.85 with a GMM kernel compared to 10.15 and 196.73 respe ctively with a Gaussian kernel. In spite of their success, the main bottleneck to their adoption is th e slow sampling speed, usually requiring hundreds to thousands of denoising steps to generat e a sample. Denoising Diffusion Implicit Models (DDIM) (Song et al., 20 21) accelerate sampling from Denois-ing Diffusion Probabilistic Models (DDPM) (Ho et al., 2020) by hypothesizing a family of non-Markovian forward processes, whose reverse process (Marko vian) estimators can be trained with the same surrogate objective as DDPMs, assuming the same par ameterization for reverse estimators. In other words, one can sample with a pretrained DDPM denoiser by designing a dif ferent forward/backward process than the original DDPM given that the forward marginals are t he same.