Hacker News Reader

I think I can probably run Gemma 3 12B on my macbook M3 pro with 18GB. The question is, should I do it? This small model is probably not capable of doing a lot or advanced coding or reasoning. What else could it be used for, since it can run locally and privately?

View on HN

A quantized Qwen3.6-35B-a3b can run in a similar footprint to gemma 12b, but is smarter. It can do coding tasks, if you specify them at a finer-grain than with bigger models.

Context limit is far too small to do anything serious, tbh.

Reply on news.ycombinator.com