Bedovyy
/

Qwen3-32B.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

Qwen3-32B.w8a8 / recipe.yaml

Bedovyy's picture

Upload folder using huggingface_hub

66a0a58 verified 7 months ago

history blame contribute delete

199 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.7}
	GPTQModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: W8A8
	dampening_frac: 0.01