Local models
Running LLMs on your own hardware
Last edited .
Tools
- Ollama
- LM Studio - with a GUI
- Foundry Local - Microsoft’s on-device runtime
- AI Dev Gallery - Microsoft’s Windows app of on-device samples; works nicely with Phi and Intel silicon
See also: Building with LLMs for prompting, agents and coding assistants.
Still stuck? Work with me or get in touch.