D_AU - Higher Precision GGUFs / Imatrix Plus Collection Models compressed in higher precision with parts of the model compression remaining in F16/full precision. Increases overall quality in all tasks. • 35 items • Updated 2 days ago • 6
view article Article Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU! By lyogavin • Apr 21 • 41