← Back to catalog

Local LLMs for Coding

Run capable coding models on your own hardware

2 modules · 3 lessons

Choose, run, and orchestrate local LLMs for real coding work: quantization, context windows, tool-calling, and wiring a local model into an agentic workflow without sending your code to the cloud.

Curriculum

Running models locally

Hardware, quantization, and serving.

  • The local-first caseFree preview
    Preview
  • Quantization & context
    Locked

Local agents

Tool-calling and orchestration on-device.

  • Tool-calling with local models
    Locked

Prefer it live?

Join an upcoming cohort for live sessions and 1:1 time.