Qwen3.5-35B-A3B
XXL GGUF quant of https://huggingface.co/Qwen/Qwen3.5-35B-A3B
MoE models degrade fast in qunats, tried to keep all important layers in BF16.
REUPLOAD with even more BF16 and Q4 & Q5 - Q6 was a little to big.
在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对，然后提交。你只需开始做种，并粘贴你账户中的密钥。它只读取你的文件，绝不修改。如果愿意，可以先阅读脚本。
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo altomek/Qwen3.5-35B-A3B-XXL-GGUF ./model-folderXXL GGUF quant of https://huggingface.co/Qwen/Qwen3.5-35B-A3B
MoE models degrade fast in qunats, tried to keep all important layers in BF16.
REUPLOAD with even more BF16 and Q4 & Q5 - Q6 was a little to big.