Task
Other
Q
toxzak/Qwen3.6-27B-Q1_K-GGUF
Other·toxzak· 930
FABQ-RC (Fisher-Adaptive Binary Quantization with Residual Codebooks) is a 1-bit quantization method for large language models that adapts per layer rather than using a fixed blocksize. This quantization of Qwen3.6-27B achieves ~1.18 bits per parameter while maintaining quality through four key innovations.
# pull & run locally
pip install mlforge-sdk && mlforge pull toxzak/Qwen3.6-27B-Q1_K-GGUF
pip install mlforge-sdk && mlforge pull toxzak/Qwen3.6-27B-Q1_K-GGUF
Model details
Provider
toxzak
Framework
gguf
Size
3.1 GB
License
apache-2.0
Downloads
930
Updated
2026-06-09
About toxzak/Qwen3.6-27B-Q1_K-GGUF
FABQ-RC (Fisher-Adaptive Binary Quantization with Residual Codebooks) is a 1-bit quantization method for large language models that adapts per layer rather than using a fixed blocksize. This quantization of Qwen3.6-27B achieves ~1.18 bits per parameter while maintaining quality through four key innovations.