mseri

Joined 12 years ago

Karma
1,933
Submissions
263
Member since
Feb 13
[ my public key: https://keybase.io/mseri; my proof: https://keybase.io/mseri/sigs/djivsidmp7PK-2ljjWHxEw4mKktD17oBpYoEZRpPNhs ]
View on Hacker News

Recent submissions

Comment · 3 months ago
Ok, done: https://github.com/mseri/zunzuncito My main focus is systems with very low ram. On my M1 with 8Gb or RAM llama.cpp cannot run gemma4 26b, but this implementation works fine with 5-6 tok/s.

I also replaced my crap implementation of the oai server following yours, I hope it's all right. I did add a mention to your project and this fact in the README. It is a lot more barebones than what you have, but I have to admit that it works really nicely for me

Comment · 3 months ago
Nice!

I had done the exact same with gemma4 26b, both for my Intel laptop and for my M1 with 8Gb RAM (with also q4 and turboquant). I don’t use it much since there are dumber but way faster models to run, but I should clean up the code and make it available

Comment · 10 months ago
Finally! Great to hear. I had the exact same experience, but gave up at the moment of ID verification… too much hassle indeed
Comment · 11 months ago
Comment · 11 months ago
Thanks indeed!
Comment · 11 months ago
Comment · 1 year ago
Comment · 1 year ago
I just want to say thanks to him!

And very poor article by Politico

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton