Vicky Boykis:

Early on, models were slow, hard to use, and just not that accurate for most programming tasks. The idea that local models were severely lagging behind was largely true until, for me, the release of GPT-OSS. I have no concrete scientific evidence of this - my own personal vibe metric of “is a model good enough” is, “do I have to double-check it against an API model”, and GPT-OSS was the first one where I started doing that a lot less often.

As a result, I’ve mostly been using local models as fast, personalized Google for development questions that don’t require recency.

But with the most recent releases from Google in the Gemma 4, family, I’ve finally been able to do agentic coding locally and have loops work at about ~75% the accuracy/speed of frontier models, which is incredible.

También, por si no lo sabías, macOS 27 Golden Gate incluye un CLI para los Foundation Models. Es decir, todas las instalaciones de macOS Golden Gate van a traer un modelo con 20B de parámetros por default.

El futuro del desarrollo con LLMs es local. No me cabe duda. Tal vez no sea 100 % viable para todos, pero la dirección es innegable.