A simple, interactive CLI for fine-tuning small language models on Apple Silicon — built by the Nano Collective, a community collective building AI tooling not for profit, but for the community. Everything we build is open, transparent, and driven by the people who use it. AI done right.

No YAML configs, no complex flags — just an interactive TUI that guides you through each step. Nanotune handles the MLX and llama.cpp tooling for you automatically.

npm install -g @nanocollective/nanotune nanotune init nanotune data add nanotune train nanotune export nanotune benchmark

Or run directly with npx:

npx @nanocollective/nanotune init

Full documentation is available online at docs.nanocollective.org or in the docs/ folder:

• Getting Started — Installation, requirements, and your first project
• Commands — Full reference for all CLI commands
• Guides — Training data, benchmarking, LLM judge, and tuning tips
• Configuration — Project config, recommended models, and judge setup
• Community — Contributing, Discord, and how to help

The Nano Collective is a community collective building AI tooling for the community, not for profit. We'd love your help!

• Contributing: See CONTRIBUTING.md for development setup and guidelines
• Discord: Join our server to connect with other users and contributors
• GitHub: Open issues or join discussions on our repository