I'm keeping this up for archival purposes but I recommend using this model instead: https://huggingface.co/pegasus912/gemma 4 31b it qat heretic ud q4 k xl Quantized from https://huggingface.co/coder3101/gemma 4 31B it qat q4 0 unquantized heretic using Quant em (https://github.com/thomas9120/Quant em)
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy