Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remains: top-performing systems are either closed-source or computationally prohibitive, precluding the on-premises deployment required for patient privacy and PHI compliance. We introduce MEDGPT-OSS, an open-weight, 20B-parameter generalist vision-language model designed to facilitate open research in clinical AI. Rather than relying on architectural complexity, MEDGPT-OSS pairs the GPT-oss language backbone with a visual front-end via a optimized, three-stage training curriculum. By progressively domain-adapting these modules through rigorous data curation and long-context multimodal alignment, we demonstrate that a 20B model can bridge the capacity gap. It successfully outperforms larger open medical models on out-of-distribution (OOD) multimodal reasoning and complex text-only clinical tasks. By unifying diverse modalities under a single instruction-following interface, MEDGPT-OSS maintains a parameter-efficient footprint fully compatible with commodity GPUs. We release the complete training recipe, open-weight checkpoints, and a rigorous evaluation harness to serve as a verifiable foundation for privacy-preserving, institution-specific clinical AI research.
@article{arxiv.2603.00842,
title = {MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine},
author = {Kai Zhang and Zhengqing Yuan and Cheng Peng and Songlin Zhao and Mengxian Lyu and Ziyi Chen and Yanfang Ye and Wei Liu and Ying Zhang and Kaleb E Smith and Lifang He and Lichao Sun and Yonghui Wu},
journal= {arXiv preprint arXiv:2603.00842},
year = {2026}
}