DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to chat with a local model through LLM and Ollama with LLM

Install the Ollama plugin and run prompts against a model that stays on your machine.

Short answer: Install LLM with pip install llm; then install the plugin with llm install llm-ollama; Pull a model with ollama pull llama3.2:latest. All steps.

Who it is forA privacy-minded developer who wants a scriptable local model.

The problemHosted APIs send your text off the machine.

The outcomeA local model answering prompts from the LLM command.

What you need first

  • Python with pip, or Homebrew, pipx or uv
  • An API key for a hosted model, or a local model server such as Ollama or LM Studio
  • Plugins for providers such as Gemini

Steps

  1. Install LLM with pip install llm
  2. Install the plugin with llm install llm-ollama
  3. Pull a model with ollama pull llama3.2:latest
  4. Run llm -m llama3.2:latest 'What is the capital of France?'
  5. Start an interactive session with llm chat -m gpt-4.1 or your local model name

Prompt for your agent

With simonw/llm, run `llm install llm-ollama`, `ollama pull llama3.2:latest`, then `llm -m llama3.2:latest 'What is the capital of France?'` and report the output.

Caveat. Requires Ollama installed separately.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for simonw/llm and "Chat with a local model through LLM and Ollama"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer