Peter Kotsch

Yes. It is on the list.
We are still revising the 9-14B pipeline.
We do have an interm Qwen 3.5 9B from the experimental pipeline here:

https://huggingface.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

It matches/exceeds 27B Qwen 3.5 ; and meets in some cases 27B Qwen 3.6 performance.
There is still a lot of optimizations to do at this time.

That's insane. Thanks. I've been using that model : Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_XS

and yes its very performant already. It blew all other 9B models when it comes to my very specific benchmark task. Basically created solution in one shot! Can't believe this was possible. the 3.6 9B should be able to do even better, probably could chain it for reasonable tasks inside a harness loop to outmatch bigger models.