This build was generated as Q4_K_M. A small number of tensors were automatically kept at higher precision by llama.cpp where needed for compatibility and stability.

Recommended use

Use this build when you want the smallest practical GGUF package here while keeping text + vision capability.

Quick start

bash

llama-cli \
  -m /absolute/path/to/supergemma4-26b-abliterated-multimodal-Q4_K_M.gguf \
  -mm /absolute/path/to/mmproj-supergemma4-26b-abliterated-multimodal-f16.gguf \
  -cnv -st \
  --image /absolute/path/to/image.png \
  -p "Describe the image briefly."

kof1467/supergemma4-26b-abliterated-multimodal-gguf-4bit

SuperGemma4-26B-Abliterated-Multimodal GGUF 4bit

Included files

Validation

Quantization note

Recommended use

Quick start

kof1467/
supergemma4-26b-abliterated-multimodal-gguf-4bit