A habana just for inference? Are you sure? Also I see the 4 bit quants put it at...

		kristopolous 9 months ago \| parent \| context \| favorite \| on: The Llama 4 herd A habana just for inference? Are you sure? Also I see the 4 bit quants put it at a h100 which is fine ... I've got those at work. Maybe there will be distilled for running at home