Huihui Gemma 4 12B Coder โ€” GGUF Quantizations

This repository contains GGUF format quantizations of the huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated model.

Available Files:

  • Huihui-gemma-4-12B-coder.f16.gguf โ€” Original unquantized model weights (FP16).
  • Huihui-gemma-4-12B-coder.Q5_K_M.gguf โ€” High quality 5-bit quantization (Recommended balance of speed and quality).
  • Huihui-gemma-4-12B-coder.Q4_K_M.gguf โ€” Medium quality 4-bit quantization (Fastest, perfectly fits 8GB VRAM).
Downloads last month
177
GGUF
Model size
12B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for KakoRel/Huihui-gemma-4-12B-coder-GGUF