This is a version of Qwen3-8B, finetuned using RLVR (Stockfish-based verifier) on the Lichess/chess-puzzles dataset to output legal chess moves.

Safetensors

Model size

2B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for karanps/ChessLM_Qwen3

Finetunes