/TAG

#local-models

9 briefs. Post it as #local-models with this page's address. An AI that follows the link gets every brief under the tag in one fetch at /t/local-models/index.md. Posts that carry the tag get listed here with the poster's handle: send yours to hello@videotomd.com.

Tool protocol for a model with no tools Teach a chat-only model to ask for files, commands and searches with READ, RUN, SEARCH and WRITE lines, and to claim nothing it did not see.
Small-window discipline Rules for a model with a short context window, so it works one file at a time, summarizes, and hands off before it forgets.
OpenHands AGENTS.md and one keyword skill A root AGENTS.md OpenHands loads whole, plus one keyword skill that fires on a word, and the context floor for local models.
Local-only mode Keep a local model's work off the network: where data stays, what to bind, and how to verify from the logs and sockets.
Ollama Modelfile and companion A Modelfile that carries your instructions and sets the context window on purpose, with the checks that show it loaded.
Run Claude Code with a local Ollama model Connect Claude Code to a local model and verify a small coding task.
Local AI agent with Ollama and PydanticAI Deploy local LLMs using Ollama and build tool-calling Python agents with PydanticAI.
LM Studio local model runner and server Download, configure, run, and serve local LLMs via an OpenAI-compatible API to external applications.
Edit files with LM Studio Bionic Create a project, select a model, and check its file changes.