Llamacpp imatrix Quantizations of gemma 3 1b it by google Using llama.cpp release b4877 for quantization. Original model: https://huggingface.co/google/gemma 3 1b it 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 gemma 3 1b it bf16.gguf bf16 2.01GB false Full BF16 weights. gemma 3 1b it Q8 0.gguf Q8 0 1.07GB false Extremely high quality, generally unneeded but max available quant. gemma 3 1b it Q6 K L.gguf Q6 K L 1.01GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . gemma 3 1b it Q6 K.gguf Q6 K 1.01GB false Very high quality, near perfect, recommended . gemma 3 1b it Q5 K L.gguf Q5 K L 0.85GB false Uses Q8 0 for embed and output weights. High quality, recommended . gemma 3 1b it Q5 K M.gguf Q5 K M 0.85GB false High quality, recommended . gemma 3 1b it Q5 K S.gguf Q5 K S 0.84GB false High quality, recommended . gemma 3 1b it Q4 K L.gguf Q4 K L 0.81GB false Uses Q8 0 for embed and output weights. Good quality, recommended .…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy