Llamacpp imatrix Quantizations of gemma 4 31B it by google Using llama.cpp release b8746 for quantization. Original model: https://huggingface.co/google/gemma 4 31B it All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp ramalama LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format What's new: Latest fixes and chat template Download a file (not the whole branch) from below: Filename Quant type File Size Split Description gemma 4 31B it bf16.gguf bf16 61.41GB true Full BF16 weights. gemma 4 31B it Q8 0.gguf Q8 0 32.64GB false Extremely high quality, generally unneeded but max available quant. gemma 4 31B it Q6 K L.gguf Q6 K L 27.07GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . gemma 4 31B it Q6 K.gguf Q6 K 26.73GB false Very high quality, near perfect, recommended . gemma 4 31B it Q5 K L.gguf Q5 K L 22.95GB false Uses Q8 0 for embed and output weights. High quality, recommended . gemma 4 31B it Q5 K M.gguf Q5 K M 22.61GB false High quality, recommended . gemma 4 31B it Q5 K…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy