whereismyai
Chatgbc
Chatgbc is a language model that runs on a Game Boy Color written in Assembly.
ChatGBC is a language model that runs on a Game Boy Color and is written in pure SM83 assembly. It features a 374K parameter model trained on TinyStories using ternary weights and integer arithmetic. The system includes an on-screen teletype interface and an encoder that processes prompts efficiently. A second cartridge, Rei, offers conversational capabilities, remembers the user's name across power cycles, and includes a small game-like world. The project uses bit-exact integer twins for testing and validation against assembly execution.
Chatgbc at a glance
Key features
- Runs on a Game Boy Color in assembly
- Uses ternary weights without multiplication
- Features an on-screen keyboard interface
- Includes a conversational mode named Rei
- Saves conversations using battery-backed memory
- Provides a bit-exact integer twin for testing
Use it for
- Generate stories on vintage hardware
- Chat with a conversational agent named Rei
- Test low-level assembly language models
Alternatives to Chatgbc
- Strata — Runs large AI models locally on consumer gaming PCs without server reliance.
- Genkit — Provides unified APIs and local developer tools for AI application workflows.
- LangChain4j — Integrates LLMs and vector stores directly into Java applications.
- whichllm — Ranks models using real benchmarks and hardware fit instead of parameter count.
- MTPLX — It runs local models twice as fast via native MTP speculative decoding.
- Dlgo — Run LLM inference quickly in pure Go without Python or external runtimes.
- BitRun — Runs 1-bit and 1.58-bit ternary models on commodity CPUs without compilation or heavy Docker images.
- LangChain — Compose exactly the agent your use case needs from model, tools, prompt, and middleware.
- ZCode — Integrates GLM-5.3 with multi-agent workflows and remote chat control.
- GSS — Renders 3D scenes using CSS knowledge without meshes or Three.js.
- Imp — Runs local models directly on NVIDIA Blackwell hardware using native 4-bit math.
- TOON — It reduces token usage by 42.6% while maintaining JSON-equivalent accuracy.
All Chatgbc alternatives