zankich
/

Qwen3-32B-INT8

Text Generation

text-generation-inference

text2text-generation

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen3-32B-INT8 / recipe.yaml

zankich's picture

initial commit

bdaae7c verified 14 days ago

history blame contribute delete

172 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: W8A8