Llamacpp imatrix Quantizations of Gemma 4 31B StyleTune by Gryphe Using llama.cpp release b9590 for quantization. Original model: https://huggingface.co/Gryphe/Gemma 4 31B StyleTune 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 Atomic Chat Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Gemma 4 31B StyleTune bf16.gguf bf16 64.23GB true Full BF16 weights. Gemma 4 31B StyleTune Q8 0.gguf Q8 0 34.13GB false Extremely high quality, generally unneeded but max available quant. Gemma 4 31B StyleTune Q6 K L.gguf Q6 K L 28.57GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Gemma 4 31B StyleTune Q6 K.gguf Q6 K 27.88GB false Very high quality, near perfect, recommended . Gemma 4 31B StyleTune Q5 K L.gguf Q5 K L 24.45GB false Uses Q8 0 for embed and output weights. High quality, recommended . Gemma 4 31B StyleTune Q5 K M.gguf Q5 K M 23.58GB false High quality, recommen…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy