News for hackers. Stuff that matters.

A comment on Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac. Parent comment

Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by kccqzy on Wednesday July 29, 2026 @03:21PM (#49101807)
I’m a bit skeptical. Without instructional materials from textbooks, programming language reference manuals and guides, as well as general knowledge about logic and discrete mathematics, I doubt a model could work very well.
[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by kanbankaren on Wednesday July 29, 2026 @03:32PM (#49101950)
Yes. Model would be limited in its performance, but it would perform well in the limited domain because LLM interpolate from training data. They don't think like humans.

We might think that knowledge from logc and discrete math would spill over to coding. Unfortunately, it doesn't seem to work like that. Even 1T parameter LLM fail on tasks if there are no variants of it in the training data.

[ Parent | on HN ]