News for hackers. Stuff that matters.
Re:Gemma 4 QAT models: Optimizing compression for mobile and... by dofm on Monday June 08, 2026 @01:17AM (#48441560)
To briefly follow up, as of yesterday llama.cpp can do Gemma 4's MTP, so I have this working at least initially — details here:

https://news.ycombinator.com/item?id=48441450

There are no comments on this comment yet.