RedHatAI
/

gemma-3-27b-it-quantized.w8a8

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

gemma-3-27b-it-quantized.w8a8 / processor_config.json

Shubhra Pandit

Upload model files

de854c7 8 months ago

history blame contribute delete

70 Bytes

	{
	"image_seq_length": 256,
	"processor_class": "Gemma3Processor"
	}