Set Up CLI Coding Agents with Local Inference

Basic idea

Use Ollama on your hardware platform to run a local coding model and connect a CLI coding agent. This playbook supports three options: Claude Code, OpenCode, and Codex CLI. Each agent is wired up with Ollama's built-in launch method (ollama launch <agent>), so you can work without environment variables, provider config files, or external cloud APIs.

Choose your CLI agent

Pick the tab that matches the CLI agent you want to use:

• Claude Code: Fastest path to a working CLI agent with a local Ollama model.
• OpenCode: Open-source CLI installed locally, then configured and launched through Ollama.
• Codex CLI: OpenAI Codex CLI launched directly from Ollama against the local model.

What you'll accomplish

You'll run a local coding model (Qwen3.6) on your hardware platform with Ollama, launch your chosen CLI agent against it with a single command, and complete a small coding task end-to-end.

What to know before starting

Required:

• Comfort with Linux command line basics
• Experience running terminal-based tools and editors
• Familiarity with Python for the short coding task

Optional:

• Experience browsing models on the Ollama library (for example, Qwen3.6)

Supported hardware platforms

Use the matrix below to confirm your hardware platform, recommended default local settings, and whether multi-node applies.

Prerequisites

Hardware requirements

• Supported hardware platform — see Supported hardware platforms matrix above
• Hardware platform powered on, networked, and reachable for local or SSH terminal access
• Sufficient memory for your chosen Qwen3.6 variant (about 23 GB for the default MTP Q4_K_M; about 39 GB for q8_0; about 71 GB for bf16)
• Enough free storage for model downloads

Software requirements

• A current Ollama release (required for ollama launch and the default MTP Q4_K_M model): ollama --version
• Internet access to download model weights
• For Codex CLI: Node.js / npm available to install @openai/codex
• Python 3 with venv support for the optional coding-task verification

Find model recipes

Browse models you can pull and run with Ollama in the Ollama library. Use the tags and sizes that fit your hardware platform’s memory and storage.

Use the Claude Code, OpenCode, or Codex CLI tab for the base workflow.

Time & risk

• Estimated time: 20 MIN (mostly model download time)
• Risk level: Low
  • Large model downloads can fail if network connectivity is unstable
  • Ollama must support ollama launch and the default MTP Q4_K_M model tag — verify with ollama --version and install from ollama.com/download if needed
• Rollback: Stop Ollama and delete the downloaded model from ~/.ollama/models (see Cleanup in each agent tab). Cleanup is optional and removes downloaded model files.
• Last Updated: 08/03/2026
  • Set up Claude Code, OpenCode, or Codex CLI against a local Qwen3.6 model with ollama launch on supported hardware platforms