XCollab
/

Llama-3.2-1B-4bit-gptq

Text Generation

4-bit precision

Model card Files Files and versions Community

Llama-3.2-1B-4bit-gptq / quant_config.json

codewithdark's picture

Add 4-bit GPTQ model quantized from meta-llama/Llama-3.2-1B (2025-06-25 10:08:23)

784b2f1 verified 23 days ago

history blame contribute delete

80 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"desc_act": true,
	"damp_percent": 0.01
	}