> edit: on bigger tests, got it to loop pretty easily unfortunately, probably local settings.

Been playing around for a few hours with the poolside/Laguna-S-2.1-NVFP4 + poolside/Laguna-S-2.1-DFlash-NVFP4 + vLLM, been seeing the same behaviour. Usually new model releases are plagued with issues at release though, best to wait 1-2 weeks then retry, or better yet, investigate yourself :) Personally I haven't found any obvious issues.

What inference server are you using? They have a custom branch for llama.cpp, but I wouldn't be surprised at all if it still needs fixing.