RedHatAI
/

gemma-3-4b-it-quantized.w8a8

Image-Text-to-Text

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

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

Shubhra Pandit

Upload model files

c66a61b 11 days ago

history blame contribute delete

70 Bytes

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