Chaturanga Nano
Chaturanga is a lightweight SLM designed for playing chess using natural language move generation. It is based on the Supra family (https://huggingface.co/collections/SupraLabs/supra2) which allows it to generate (mostly)accurate and legal moves whilst keeping memory footprint to a minimum. It's small size (25M-100M parameters) allows it to run comfortably on laptop grade GPUs and CPUs.
Chaturanga Nano is a 25M variant based on the Supra2-Medium-Base which has been finetuned on 200,000 rows from the chessllm dataset. Despite its small size, it can still generate fairly precise and legal moves in SAN.
The Chaturanga model comes in the following sizes: Nano, Neo(Nano+), Mini, Pro and Ultra(Pro+)
You can test it out via. the files in the GitHub page here
Estimated parameters: ~25M
Architecture: Qwen3
Intended use: as an experimental chess-playing SLM
Training data
- Source: chessllm dataset (https://huggingface.co/datasets/mlabonne/chessllm)
- Rows: ~200,000 rows templated in SAN (Standard Algebraic Notation)
- Training: trained for 5,000 steps on an RTX 3050 (4GB VRAM)
Usage
The model and the chess GUI can be found on the GitHub page
Limitations
- The model only has 25M parameters, so hallucinations and illegal moves may occur.
- Model for experimental use only; users should employ it as such under license.