ChessNano
What it is
ChessNano is a sub-50M parameter autoregressive transformer that learns to play chess by predicting Standard Algebraic Notation (SAN) move sequences. It uses advanced quantization techniques (TurboQuant QAT) and Tree-of-Thought inference to maintain high legal move rates while remaining small enough to run on a CPU.
The problem it solves
High memory and compute requirements for chess engines and large language models.
What you could use it for
- On-device chess move prediction
- Low-resource chess AI inference
- Researching quantization-aware training (QAT) for small transformers
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.