karuko24
/

Qwen3-30B-A3B-W4A16

compressed-tensors

Model card Files Files and versions Community

Qwen3-30B-A3B-W4A16 / recipe.yaml

karuko24's picture

Upload folder using huggingface_hub

2f6834d verified 1 day ago

history blame contribute delete

172 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	scheme: W4A16
	targets: Linear
	ignore: [lm_head, multi_modal_projector, merger, modality_projection]