Llamacpp imatrix Quantizations of SmolLM2 1.7B Instruct Using llama.cpp release b3991 for quantization. Original model: https://huggingface.co/HuggingFaceTB/SmolLM2 1.7B 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 1.7B Instruct f16.gguf f16 3.42GB false Full F16 weights. SmolLM2 1.7B Instruct Q8 0.gguf Q8 0 1.82GB false Extremely high quality, generally unneeded but max available quant. SmolLM2 1.7B Instruct Q6 K L.gguf Q6 K L 1.43GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . SmolLM2 1.7B Instruct Q6 K.gguf Q6 K 1.41GB false Very high quality, near perfect, recommended . SmolLM2 1.7B Instruct Q5 K L.gguf Q5 K L 1.25GB false Uses Q8 0 for embed and output weights. High quality, recommended . SmolLM2 1.7B Instruct Q5 K M.gguf Q5 K M 1.23GB false High quality, recommended . SmolLM2 1.7B Instruct Q5 K S.gguf Q5 K S 1.19GB false High quality, recommended . SmolLM2 1.7B Instruct Q4 K L.gguf Q4 K L 1.08GB 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