Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...
💡 TL;DR: This project creates a local proxy server that gives you free access to GPT-4o, Claude, DeepSeek, Gemini, Grok, Mistral, and Qwen models through Puter.js SDK - no expensive API keys needed!
Some results have been hidden because they may be inaccessible to you
Show inaccessible results