I think they only claim their "Ling-Lite" 17B model can fit on a single 96GB GPU...

		cavisne on March 28, 2025 \| parent \| context \| favorite \| on: Every Flop Counts: Scaling a 300B LLM Without Prem... I think they only claim their "Ling-Lite" 17B model can fit on a single 96GB GPU, their 300B model needs 8 of them (768GB of HBM)