gemma-4-26B-A4B-it

BaseRT .base builds of google/gemma-4-26B-A4B-it for fast local inference on Apple Silicon (Metal).

Files

File	Precision	Size
gemma-4-26B-A4B-it-Q4.base	4-bit	16.1 GB
gemma-4-26B-A4B-it-Q8.base	8-bit	26.7 GB

Usage

curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/gemma-4-26B-A4B-it
basert chat basecompute/gemma-4-26B-A4B-it

The 8-bit build is best suited to systems with 32 GB or more of unified memory; the 4-bit build runs comfortably on 16–24 GB.

Released under the gemma license, inherited from the base model.