static quants of https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
To run these quants before https://github.com/ggml-org/llama.cpp/pull/12843 is merged you will need to build llama.cpp from https://github.com/ymcki/llama.cpp
static quants of https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
To run these quants before https://github.com/ggml-org/llama.cpp/pull/12843 is merged you will need to build llama.cpp from https://github.com/ymcki/llama.cpp