The llamay blog
Long-form on running language models on hardware you own: local inference, prompt caching, GGUF quantisation, tool calling, structured output, and what any of it actually costs once the tokens are yours.
-
Your inference bill is mostly prefill, and you are paying it twice
Most teams price an LLM feature by output tokens and are surprised by the invoice. The prompt is the expensive half, it is usually identical every call, and there is a way to stop paying for it twice.
-
How to run an LLM locally in 2026, and which one fits your machine
Five minutes from nothing to a model answering on your own hardware, plus the sizing table that decides whether you want a 3B, a 7B or a 70B.
-
How to cut LLM latency with prompt caching
This article explains how prompt caching reduces latency in large language models.
-
Ollama vs llama.cpp vs llamay: picking a local inference server
Three ways to serve a GGUF file on your own hardware, what each one is actually optimising for, and the one capability only one of them has.
RSS · one article a day, written on llamay.