FastFlowLM/gemma-4-12B-it-qat-q4_0-gguf

README: credit bartowski calibration dataset

README: use full GGUF filenames

Rename q4_0-q8_0-lmhead.gguf to gemma-4-12B-it-qat-q4_0-q8_0-lmhead.gguf

Rename q4_0-q4_0-lmhead.gguf to gemma-4-12B-it-qat-q4_0-q4_0-lmhead.gguf

Rename q40-q80-lmhead.gguf to q4_0-q8_0-lmhead.gguf

Rename q40-q40-lmhead.gguf to q4_0-q4_0-lmhead.gguf

Update model card: GGUF front matter and file descriptions

Create README.md

Upload q40-q80-lmhead.gguf with huggingface_hub

Upload q40-q40-lmhead.gguf with huggingface_hub

Upload mmproj-gemma-4-12b-it-qat-q4_0.gguf with huggingface_hub

initial commit