ytmytm/llama2.c64

A language model on a Game Boy Color - pure SM83 assembly

Commodore 64 knowledge base for AI-assisted development — Qdrant vector search + FalkorDB knowledge graph, served over MCP

TinyStories-260K running locally on a stock Game Boy Color.

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.

A "large" language model running on a microcontroller

Inference Llama 2 in one file of pure 🔥

Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery

LLM Frontend for Power Users.

Fully offline tiny LLM chatbot on the ESP32-S3 Cardputer ADV - 8M params, Q4 weights baked into the firmware, ~5 tok/s.