nytopop
/

Qwen3-30B-A3B.w8a8

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

Qwen3-30B-A3B.w8a8 / recipe.yaml

nytopop's picture

Upload folder using huggingface_hub

6bcdc1e verified 7 months ago

history blame contribute delete

147 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head, 're:.*mlp.gate$']
	targets: [Linear]
	scheme: W8A8