google

/

gemma-3-27b-it

like 1.57k

Follow

Google 25.8k

Hi,
Thank you for the release of the google/gemma-3-27b-it model! I have a couple of questions regarding fine-tuning:

1. Is there an AWQ (Activation-aware Weight Quantization) version of this model available, or are there any plans to release one in the future? It would be helpful to have a quantized version available for lower memory usage.

2. If an AWQ-quantized version is available, is it possible to directly perform QLoRA fine-tuning on it?