Nice! It is indeed very fast for me. With the same settings and the mixture model, it’s 10x faster than ABCSMCPR and 3x faster than ApproxBayes. If it works as well for more complex models, it will be quite a nice speed up for some of my work.
You used the algorithm from Turner et al. 2012 for ABCDE? Are there any downsides relative to SMC of which to be careful?