altomek
/

Gemma-4-26B-A4B-it-XXL-GGUF

Image-Text-to-Text

Model card Files Files and versions

Gemma-4-26B-A4B-it

GGUF quant of https://huggingface.co/google/gemma-4-26B-A4B-it

Changelog

reupload 1: better recipe to quantize weights = smaller quant & better performance + BOS added
reupload 2: updated chat_template as in: https://huggingface.co/google/gemma-4-26B-A4B-it/discussions/21
reupload 3: added updated tokenizer_config.json

Downloads last month: 877

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

Log In to add your hardware

Model tree for altomek/Gemma-4-26B-A4B-it-XXL-GGUF

Base model

google/gemma-4-26B-A4B-it

Quantized

(153)

this model

Collection including altomek/Gemma-4-26B-A4B-it-XXL-GGUF

XXL GGUF

Inspired by Unsloth XL quants, I started mastering my own GGUF quants with gool to make them even better then XL ones. • 13 items • Updated 5 days ago