Jay Luong, Author at Geek Bacon

Understanding VRAM Usage in Ollama with Large Models

Posted by Jay Luong | May 3, 2025 | Networking |

Running large language models (LLMs) like Qwen3-235B using ollama on a multi-GPU setup involves a...

Posted by Jay Luong | May 1, 2025 | CMS |

Which Self-Hosted CMS Makes AI Integration Easiest? If you’re building modern content...

Posted by Jay Luong | May 1, 2025 | AI Agents |

AI Agents are rapidly transforming how we interact with technology, capable of performing complex...

Posted by Jay Luong | Apr 19, 2025 | CI/CD, Networking |

Blog Post HTML From Code to Live App in Your Homelab: Your Personal Cloud, No Bills Attached! Ever...

Posted by Jay Luong | Apr 16, 2025 | Networking |

In today’s rapidly evolving tech landscape, the concept of “vibe coding” has...