Qwen3.6-27B-FABQ-RC-GGUF
FABQ-RC quantized model in GGUF Q1_K format.
Files
| File | Description |
|---|---|
Qwen3.6-27B-Q1_K.gguf | FABQ-RC weights in GGUF Q1_K format |
quantized_model.pth | Original FABQ-RC compressed weights |
Use
./llama-cli -m Qwen3.6-27B-Q1_K.gguf -n 256 -p "Your prompt"
Citation
@misc{fabqrc2026,
author = {Zach Maronek},
title = {FABQ-RC: Fisher-Adaptive Binary Quantization with Residual Codebooks},
year = {2026},
url = {https://github.com/toxzak/fabq-rc}
}