Experiences with local models for coding

Birgitta Böckeler, writing on Martin Fowler's influential technology platform, has been testing local language models specifically for coding—AI systems that run on your own machine rather than in the cloud. She compared several models using two standard programming tasks and then deployed the most promising candidate into her day-to-day workflow. The broader goal: understand whether local models can serve as a practical alternative to cloud-based coding assistants, with potential advantages including lower costs and keeping source code on-premises.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton