Blog

Deep dives on local-first AI agents

Subscribe
Claude in a hard hat points at a blueprint while the Atomic Agent mascot builds a toy house at a home desk next to a glowing desktop computer Latest
Guide

How to Use Claude Code with a Local LLM (and When to Keep Claude in the Loop)

Point Claude Code at a local LLM with Ollama, llama.cpp, LM Studio or vLLM: exact env vars, the limits you will hit, and a hybrid setup that keeps a cloud model.

Nadya Dudka and Andrew Dyuzhov 10 min read
Read article

All posts

Newsletter

New benchmarks and guides in your inbox

Model tests we actually ran, local setup notes, and release news. No spam, unsubscribe any time.

Atomic Agent mascot pressing a purple Qwen logo chip into a graphics card on a workbench

How to Run Qwen 3.8 27B Locally

Run Qwen 3.8 27B as a tool-using agent on your own machine: memory math for 24 GB cards, grammar-constrained tool calls, and two measured agent runs.

Guide 8 min

Run your local agent
in one click