---
title: Local LLMs, Ollama Models and AI Tooling | Relic
description: Running language models on your own hardware: which Ollama models fit your machine, how local LLMs compare, and how to use AI tools without leaking data.
canonical: https://relic.space/blog/topics/local-ai
source: https://relic.space/llms.txt
---
Topic

# AI on your machine

You do not need a cloud account to use a capable language model. Relic runs its AI on-device for privacy, and the same idea scales up: these guides cover the models you can run yourself and the tooling growing around them.

Start here

[Pillar·10 minOllama models: how to choose and run themOllama runs language models on your own hardware with almost one command. The catch is picking one your machine can hold. How to read a model listing, do the RAM math, and run it.Read ](https://relic.space/blog/ollama-models)

In this topic

[7 minThe best local LLM depends on your hardwareThe best local LLM is the smallest one that does your task and fits your memory. A buyer's guide organized by hardware tier and task, with honest evaluation advice.Read ](https://relic.space/blog/best-local-llm)[7 minClaude Code vs Cursor: an even-handed comparisonClaude Code is a terminal agent you delegate tasks to; Cursor is an AI-first editor you stay inside. A fair comparison of form factor, interaction and where each one shines.Read ](https://relic.space/blog/claude-code-vs-cursor)[8 minPrompt injection examples, explained for defendersPrompt injection turns untrusted data into instructions a model obeys. The categories of prompt injection examples, why they work, and how to defend without pretending it is solved.Read ](https://relic.space/blog/prompt-injection-examples)
