Use local Ollama models in ChatGPT Desktop (Codex app)

Melvin Vivas · X post · 2026-09-11 · Open on X

Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: beginner

Summary

ChatGPT Desktop (the Codex app) can now be set up, through a plugin, to use local models served by Ollama. You need Ollama 0.34 or later.

Key points

• ChatGPT Desktop / the Codex app can use Ollama models through a plugin.
• Requires Ollama version 0.34 or later.
• Lets you run local models inside the ChatGPT/Codex desktop experience.

Resources mentioned

• Ollama · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Open-source tool for downloading and running LLMs on your own machine with minimal setup.
  Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), Running Qwen3.8-27B Locally on an M5 Max MacBook with Inco Splash (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 12 more
• Codex Desktop · tool · developers.openai.com · check price
  OpenAI's desktop app, which can now be configured to use Ollama models through a plugin.
  Also in: Codex Desktop as a General Assistant Beyond Coding (Melvin Vivas on X · notes)

Try this

• Download or update to Ollama 0.34, then set up ChatGPT Desktop to use Ollama models through the plugin.