IIGroup/X-Coder-RL-Qwen3-8B
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jan 10, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

IIGroup/X-Coder-RL-Qwen3-8B is an 8 billion parameter code reasoning foundation model developed by IIGroup, built upon the X-Coder-SFT-Qwen3-8B base model. It is specifically trained with Reinforcement Learning from Human Feedback (RLHF) on fully synthetic RL data, utilizing the GRPO training method. This model achieves strong performance in competitive programming tasks, making it highly suitable for code generation, problem-solving, and advanced code reasoning applications.

Loading preview...