Prioritized ctx over bpw for this one since it's primarily an agentic model. Would recommend Gemma 4 31B instead for non-agentic.
5.10 bpw, a mixture of Q5_K and Q4_K
Fits ~90k F16, ~170k Q8 CTX on a 24GiB GPU using Vulkan
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 Beinsezii/Qwen3.6-27B-5.10BPW-GGUF ./model-folderPrioritized ctx over bpw for this one since it's primarily an agentic model. Would recommend Gemma 4 31B instead for non-agentic.
5.10 bpw, a mixture of Q5_K and Q4_K
Fits ~90k F16, ~170k Q8 CTX on a 24GiB GPU using Vulkan