Llamacpp imatrix Quantizations of SmolLM2 360M Instruct Using llama.cpp release b3991 for quantization. Original model: https://huggingface.co/HuggingFaceTB/SmolLM2 360M Instruct All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description SmolLM2 360M Instruct f16.gguf f16 0.73GB false Full F16 weights. SmolLM2 360M Instruct Q8 0.gguf Q8 0 0.39GB false Extremely high quality, generally unneeded but max available quant. SmolLM2 360M Instruct Q6 K L.gguf Q6 K L 0.37GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . SmolLM2 360M Instruct Q6 K.gguf Q6 K 0.37GB false Very high quality, near perfect, recommended . SmolLM2 360M Instruct Q5 K L.gguf Q5 K L 0.29GB false Uses Q8 0 for embed and output weights. High quality, recommended . SmolLM2 360M Instruct Q5 K M.gguf Q5 K M 0.29GB false High quality, recommended . SmolLM2 360M Instruct Q5 K S.gguf Q5 K S 0.28GB false High quality, recommended . SmolLM2 360M Instruct Q4 K L.gguf Q4 K L 0.27GB false Uses Q8 0 for embed and output weights. Good quality, recommende…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy