NexesQuants
/

llama-3-70B-Instruct-abliterated-CQ-GGUF

Create README.md

762a321 verified about 1 year ago

132 Bytes

	Custom GGUF quant for :
	failspy/llama-3-70B-Instruct-abliterated-GGUF

	Optimal (8k ctx) for 36GB VRAM with an IGP displaying the OS.