Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer. - HarryR/z80ai

Hacker News is a community-driven platform for sharing and discussing technology news, startups, and programming-related topics. Through user submissions and comments, Hacker News offers insights into emerging technology trends, industry developments, and entrepreneurial ventures. Readers can participate in discussions, share their insights, and stay informed about the latest advancements in technology and innovation.

Hacker News

Z80-μLM is a 2-bit quantized language model designed to run on an 8-bit Z80 processor with 64KB RAM, packaged as a 40KB CP/M binary. The project uses trigram hash encoding for input, 2-bit weight quantization, and 16-bit integer inference without floating-point operations. It includes pre-built examples like a conversational chatbot and a 20 Questions game, demonstrating how to train compact models in Python and export them for vintage hardware. The implementation features tight Z80 assembly loops for multiply-accumulate operations and quantization-aware training to handle the processor's constraints.

HarryR/z80ai: Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vi