Local-first

LM Studio with Meridian

Load Meridian GGUF models directly in LM Studio and query them through the built-in OpenAI-compatible local server. Zero telemetry, fully offline.

Quickstart

  1. Download LM Studio for your platform.
  2. Search “Meridian” in the model explorer or sideload a Meridian GGUF from our model hub.
  3. Start the local server on port 1234.
  4. Point any OpenAI-compatible client to http://localhost:1234/v1.

Usage

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:1234/v1",
  apiKey: "not-needed",
});

const completion = await client.chat.completions.create({
  model: "meridian-7b",
  messages: [{ role: "user", content: "Hello" }],
});

The LM Studio SDK wraps the same endpoint. Use whichever fits your stack.

🔒

Runs entirely on your machine

Meridian + LM Studio keeps every token local. No API keys, no cloud round-trips, no logging. Your data never leaves the device.

← All integrationsOllama →