Show HN: Nibia Fabric – Turn everyday computers into a shared AI compute cluster
I built NIBIA Fabric, an open-source distributed LLM inference system that pools CPU and RAM across macOS, Linux, and Windows machines. It builds on llama.cpp, with capacity-aware scheduling, adaptive memory reservation, persistent tensor caching, and an OpenAI-compatible API. I’ve validated the current alpha on three physical machines across several models, including a 30B-class Qwen model, as well as GPT-OSS 20B. Feedback on the architecture and use cases is very welcome.
阅读原始来源
来源记录
指标快照
points · 1 votes
2026-10-31 12:30:22.362Z
cumulative since publication
研究分析
项目记录
仓库：nibia-ai/fabric。 来源描述：I built NIBIA Fabric, an open-source distributed LLM inference system that pools CPU and RAM across macOS, Linux, and Windows machines. It builds on llama.cpp, with capacity-aware scheduling, adaptive memory reservation, persistent tensor caching, and an OpenAI-compatible API. I’ve validated the current alpha on three physical machines across several models, including a 30B-class Qwen model, as well as GPT-OSS 20B. Feedback on the architecture and use cases is very welcome.
采用记录与比较对象
来源票数: 1 votes (2026年10月31日 UTC; cumulative since publication)；前次同口径记录为 1（2026年10月31日 UTC），两个观测值不等于需求增长。 可供比较的近期同类记录：“D4Vinci/Scrapling” (GitHub Trending, 2026年11月5日)；“garrytan/gstack” (GitHub Trending, 2026年11月5日)。主题相近仅用于导航，未核验其是否属于同一需求或独立证据。
采用判断
应与它要替代的工具或人工流程比较。现有记录支持发现项目，尚不能确认可靠性、运行成本优势或商业采用。
尚未核验的门槛
尚未核验：许可证权限、硬件要求、安装步骤、维护状态，以及包含失败样例的代表性任务。
下一步试验
选择一个真实任务和现有替代方案，记录 commit、环境、输入、输出、耗时与失败行为；保留结果后再给出采用建议。