HuatuoGPT-3 is FreedomIntelligence’s named medical language-model series, comprising 9B and 27B checkpoints based on Qwen3.5-9B and Qwen3.8-27B respectively. One-stage Policy Optimization adapts the models through medical reinforcement learning without preceding domain-specific supervised fine-tuning, using teacher guidance that is retired as performance improves. Apache-licensed weights, training code, data, and a rubric grader are published. Inference requires thinking mode and generates reasoning before a final response. Vision-capable backbones are retained, but the released model-card examples and medical evaluations focus on textual questions. September 2026 weight publication is verified; first-day precision remains unresolved.

HuatuoGPT-3

HuatuoGPT

Research group developing HuatuoGPT medical language models and open medical AI training methods, datasets, and evaluations.

FreedomIntelligence

FreedomIntelligence Model Families

HuatuoGPT-3