Llamacpp imatrix Quantizations of Nemotron 3 Nano 30B A3B by nvidia Using llama.cpp release b7423 for quantization. Original model: https://huggingface.co/nvidia/NVIDIA Nemotron 3 Nano 30B A3B BF16 All quants made using imatrix option with dataset from here combined with a subset of combined all small.parquet from Ed Addario here Run them in LM Studio Run them directly with llama.cpp, or any other llama.cpp based project Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Nemotron 3 Nano 30B A3B bf16.gguf bf16 63.18GB true Full BF16 weights. Nemotron 3 Nano 30B A3B Q8 0.gguf Q8 0 33.51GB false Extremely high quality, generally unneeded but max available quant. Nemotron 3 Nano 30B A3B Q6 K L.gguf Q6 K L 33.43GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Nemotron 3 Nano 30B A3B Q6 K.gguf Q6 K 33.43GB false Very high quality, near perfect, recommended . Nemotron 3 Nano 30B A3B Q5 K L.gguf Q5 K L 26.26GB false Uses Q8 0 for embed and output weights. High quality, recommended . Nemotron 3 Nano 30B A3B Q5 K M.gguf Q5 K M 26.15GB false High quality, recommended . Nemotron 3 Nano…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy