Llamacpp imatrix Quantizations of Mistral Small 3.1 24B Instruct 2503 by mistralai Vision is here!! Thanks ngxson! You can now download an mmproj file to enjoy all the vision goodness! https://github.com/ggml org/llama.cpp/pull/13231 Using llama.cpp release b4914 for quantization. Original model: https://huggingface.co/mistralai/Mistral Small 3.1 24B Instruct 2503 All quants made using imatrix option with dataset from 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 Mistral Small 3.1 24B Instruct 2503 bf16.gguf bf16 47.15GB false Full BF16 weights. Mistral Small 3.1 24B Instruct 2503 Q8 0.gguf Q8 0 25.05GB false Extremely high quality, generally unneeded but max available quant. Mistral Small 3.1 24B Instruct 2503 Q6 K L.gguf Q6 K L 19.67GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Mistral Small 3.1 24B Instruct 2503 Q6 K.gguf Q6 K 19.35GB false Very high quality, near perfect, recommended . Mistral Small 3.1 24B Instruct 2503 Q5 K L.gguf Q5 K L 17.18GB false Uses Q8 0 for…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy