0.6B-Reranker GGUF - Working

#7
by JonathanMiddleton - opened

I was unable to find a working 0.6B-Reranker quant so I added a set here: https://huggingface.co/JonathanMiddleton/Qwen3-Reranker-0.6B. These have been verified with ngxson's unmerged llama.cpp branch. Details in the model card.

Thank you so much for these models!

JonathanMiddleton changed discussion title from 0.6B GGUF - Working to 0.6B-Reranker GGUF - Working

Sign up or log in to comment