The story’s score and claims

Comments on No. 133 of 143 · Hacker News · edition of Wednesday 11 November 2026

You can now train your own LLMs with less memory, on your consumer GPUs

Summary

An independent AI researcher, Oguz Eldereli, posted on Hacker News a ternary-weight optimizer that cuts per-weight training memory from about 16 bytes (AdamW) to roughly 1 byte or less, reportedly letting a 27B model train on a 24GB RTX 3090.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules