Codex + Local Qwen3.8-27B (Q4_K_M) with /goal

Melvin Vivas · X post · 2026-08-30 · Open on X

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

Summary

The creator runs Codex with a local Qwen3.8-27B model quantized to Q4_K_M and gives it tasks with the /goal command. He frames this as a 'path to freedom' from cloud usage limits.

Key points

• Model: Qwen3.8-27B with Q4_K_M quantization, a common GGUF format that runs on consumer hardware.
• Harness: Codex, set up to use a local model.
• He uses the /goal command to give the agent a long-running objective.
• Motivation: independence from paid cloud usage limits.

Resources mentioned

• Qwen3.8-27B · tool · huggingface.co · free
  A 27B-parameter open-weight model from Alibaba's Qwen family that you can run locally or call through hosted APIs.
  Also in: Deploying Qwen3.8 27B on Hugging Face Inference Endpoints (Melvin Vivas on X · notes), Using Hugging Face credits: Jobs, Inference Endpoints and Open Models (Melvin Vivas on X · notes), Running Qwen3.8-27B Locally on an M5 Max MacBook with Inco Splash (Melvin Vivas on X · notes), Ternary Bonsai 2 27B: 9x smaller model keeping 98.2% of benchmark scores (Melvin Vivas on X · notes) and 24 more
• OpenAI Codex · tool · openai.com · paid
  OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
  Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more

Try this

• Try running Codex with a locally hosted, quantized model (such as Q4_K_M) and the /goal command.