vllmd
/

gemma-3-4b-it-w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions

gemma-3-4b-it-w8a8 / processor_config.json

Commit History

Introduce quantized Google Gemma 3-4b instruction tuned

a10c93a

stevendake commited on Mar 31, 2025