tranhuonglan
/

Qwen3-06B-base-quantization-modifier-w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen3-06B-base-quantization-modifier-w8a8 / recipe.yaml

tranhuonglan's picture

Upload Qwen3ForCausalLM

ea1b611 verified 12 days ago

history blame contribute delete

129 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: W8A8