Show HN: Z80-μLM, a 'Conversational AI' That Fits in 40KB
Source: Hacker News
Introduction
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays.
Z80‑μLM is a character‑level language model with 2‑bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64 KB RAM. The entire thing: inference, weights, chat …