FreedomIntelligence/HuatuoGPT-3-8B

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 20, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Warm

HuatuoGPT-3-8B by FreedomIntelligence is an 8 billion parameter medical large language model, built on the Qwen3-8B-Base architecture. It is specifically fine-tuned for medical expertise using SeedRL, an RL-only domain adaptation paradigm. This model is designed to function as a medical expert, providing detailed reasoning blocks before its final responses.

Loading preview...

HuatuoGPT-3-8B: A Medical Expert LLM

HuatuoGPT-3-8B, developed by FreedomIntelligence, is an 8 billion parameter medical large language model. It is built upon the Qwen3-8B-Base backbone and uniquely trained using SeedRL, an RL-only domain adaptation paradigm. This method transforms a base model into a specialized medical expert through a single reinforcement learning stage, distinguishing it from traditional fine-tuning approaches.

Key Capabilities & Features

  • Medical Specialization: Designed specifically for medical domain tasks, providing expert-level responses.
  • Reasoning Mode: By default, the model operates in a "thinking mode," outputting a <think>...</think> reasoning block before generating its final response. This allows users to understand the model's thought process.
  • SeedRL Training: Utilizes an innovative RL-only domain adaptation paradigm for efficient specialization.

Use Cases

  • Medical Information Retrieval: Answering complex medical questions.
  • Clinical Decision Support: Providing insights and reasoning for medical scenarios.
  • Medical Education: Assisting in learning and understanding medical concepts.

For deployment, HuatuoGPT-3-8B can be integrated with tools like vLLM or SGLang, similar to other Qwen3 models.