13:45
2026-08-18
blog.devgenius.io
developer-tools
Why I Switched from Ollama to llama.cpp — and What I Learned
A developer switched from Ollama to llama.cpp to run a Qwen2.5-14B model on a dual-GPU AMD handheld, gaining efficiency and hardware control. The switch involved locating the Ollama blob, symlinking i…