This is the high-efficiency model of the Searchless Chess project—a compact neural network that plays chess at a strong club level (~1817 ELO) relying purely on neural intuition, without any search algorithms (no minimax, no alpha-beta pruning).
| Metric | Value |
|---|---|
| ELO (Estimated) | 1817 |
| Tier 4 Puzzles (1000-1250) | 82% Accuracy |
| Tier 6 Puzzles (1500-1750) | 68% Accuracy |
| Tier 8 Puzzles (2000-2250) | 34% Accuracy |
Despite having only 2.64M parameters, this model outperforms the ResNet-XL (24.7M parameters), proving that Vision Transformers are 10x more parameter-efficient for chess. It achieves an impressive 688 ELO per million parameters, making it the most optimized model in the series.
This repository provides everything needed to run or fine-tune the model:
model.keras: Complete model (architecture + weights) in Keras 3 format.model.weights.h5: Standalone weights.config.json: Model architecture configuration.model.keras for a quick "plug-and-play" experience, as it contains both the model architecture and the trained weights in one file.config.json and model.weights.h5 if you prefer to build the model structure manually in your code and load only the parameters (e.g., for custom fine-tuning).To use this model for playing chess, use the ChessAI wrapper provided in the official GitHub repository. It handles the FEN-to-Tensor encoding and move selection logic.
# 1. Clone the repository: git clone https://github.com/mateuszgrzyb-pl/searchless-chess
# 2. Use the following code:
import chess
from src.chess_ai.core.model import ChessAI
# Load the chess engine (provide path to the downloaded model.keras)
chess_bot = ChessAI('path/to/vit-small/model.keras')
# Create a chess board
board = chess.Board()
# Play a game
board.push_san("e4") # Your move
engine_move = chess_bot.make_move(board) # Engine responds via neural intuition
board.push(engine_move)
print(board)
print(f"Engine played: {engine_move}")
For detailed instructions on board encoding, training, and evaluation, visit the Searchless Chess GitHub.
The model treats the chess board as a set of tokens. Unlike traditional CNNs that look at local patterns, the Vision Transformer uses self-attention to understand the global relationship between all pieces simultaneously (e.g., a bishop's long-range pressure on a king).
The model was trained on the Lichess Stockfish Normalized dataset, consisting of 316M deduplicated positions with evaluations.
If you use this model in your research, please cite:
@software{grzyb2025searchless,
author = {Grzyb, Mateusz},
title = {Searchless Chess: Master-Level Chess Through Pure Neural Intuition},
year = {2025},
publisher = {Hugging Face},
url = {https://huggingface.co/mateuszgrzyb/searchless-chess-vit-small}
}