CarlOwOs
/

Qwen3-0.6B-Base-FP8-Dynamic

compressed-tensors

Model card Files Files and versions Community

Qwen3-0.6B-Base-FP8-Dynamic / recipe.yaml

CarlOwOs's picture

Add FP8 dynamically quantized Qwen3-0.6B-Base model using llm-compressor

9dce9b8 verified 22 days ago

history blame contribute delete

136 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC