Switching from Ollama to llama-swap + llama.cpp on NixOS: the power user's choice 🦙

This page cannot be shown here. You can still read it on the original site — the toolbar below keeps your place in the directory.

Table of Contents The draft I never published The original trigger: broken models The catalyst: dual GPUs and control API compatibility and the “switch” My NixOS setup Compiler flags matter What I gained (and lost) Advantages of llama-swap + llama.cpp The trade-off Conclusion: maturing as an AI hobbyist The draft I never published I started writing this blog post four months ago. Back…

Read on /post/llama-nixos/ ↗