Llamacpp imatrix Quantizations of Ministral 3 3B Instruct 2512 by mistralai Using llama.cpp release b7229 for quantization. Original model: https://huggingface.co/mistralai/Ministral 3 3B Instruct 2512 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 No prompt format found, check original model page Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Ministral 3 3B Instruct 2512 bf16.gguf bf16 6.87GB false Full BF16 weights. Ministral 3 3B Instruct 2512 Q8 0.gguf Q8 0 3.65GB false Extremely high quality, generally unneeded but max available quant. Ministral 3 3B Instruct 2512 Q6 K L.gguf Q6 K L 2.92GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Ministral 3 3B Instruct 2512 Q6 K.gguf Q6 K 2.82GB false Very high quality, near perfect, recommended . Ministral 3 3B Instruct 2512 Q5 K L.gguf Q5 K L 2.57GB false Uses Q8 0 for embed and output weights. High quality, recommended . Ministral 3 3B Instru…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy