---
language:
- en
license: apache-2.0
library_name: peft
base_model: Qwen/Qwen3.8-27B
tags:
- radiology
- medical
- healthcare
- clinical-nlp
- qwen
- impression-generation
- lora
- 4bit
pipeline_tag: text-generation
widget:
- text: '[EXAM: CT CHEST]

    FINDINGS: Large saddle pulmonary embolus with right ventricular dilation (RV/LV
    ratio 1.4).'
  example_title: CT Pulmonary Embolism
- text: '[EXAM: MRI BRAIN]

    FINDINGS: Restricted diffusion in left MCA territory with abrupt flow truncation
    at M1 bifurcation.'
  example_title: Brain MRI Stroke
---

# 🩻 Qwen 3.8-27B Clinical Radiology Impression & Consultation AI

<div align="center">

[![Hugging Face Space Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Live%20Demo%20Space-blue?style=for-the-badge)](https://huggingface.co/spaces/Medico/Qwen3.8-27B-Radiology-Impression-Demo)
[![Model Size](https://img.shields.io/badge/Parameters-27B%20Dense-purple?style=for-the-badge)](#)
[![Dataset](https://img.shields.io/badge/Dataset-659K%20Clinical%20Reports-green?style=for-the-badge)](https://huggingface.co/datasets/Medico/radiology-reports-curated)
[![License](https://img.shields.io/badge/License-Apache%202.0-yellow?style=for-the-badge)](#)

</div>

---

## 🌟 Overview & Key Links

**`Medico/Qwen3.8-27B-Radiology-Impression`** is a dense 27-Billion parameter clinical foundation model fine-tuned on **659,381 real-world clinical findings-to-impression pairs** across diverse imaging modalities (CT, MRI, Chest Radiography, Ultrasound, and PET/CT).

* 🌐 **Live Interactive Web Demo**: [**Hugging Face Space Demo**](https://huggingface.co/spaces/Medico/Qwen3.8-27B-Radiology-Impression-Demo)
* 📊 **Curated Training Corpus**: [**Medico/radiology-reports-curated**](https://huggingface.co/datasets/Medico/radiology-reports-curated)
* ⚡ **Base Architecture**: `Qwen/Qwen3.8-27B` (Dense 27B model, `qwen3_5` architecture)

---

## 🚀 Free Unlimited Chat & Deployment Options

You can chat with this model with **unlimited access for free** using any of the following methods:

### Option 1: Live Web App (Instant Free Access)
Open the official Hugging Face Space:
👉 [**https://huggingface.co/spaces/Medico/Qwen3.8-27B-Radiology-Impression-Demo**](https://huggingface.co/spaces/Medico/Qwen3.8-27B-Radiology-Impression-Demo)

### Option 2: Free 1-Line Local Chat (Ollama)
Run directly on your local machine with GPU/CPU:
```bash
ollama run hf.co/Medico/Qwen3.8-27B-Radiology-Impression
```

### Option 3: Free Cloud GPU Inference (Google Colab / Kaggle / Lightning AI)
Run this Python snippet on any free GPU environment (Tesla T4, L4, A10G):

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel

BASE_MODEL = "Qwen/Qwen3.8-27B"
LORA_REPO = "Medico/Qwen3.8-27B-Radiology-Impression"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_use_double_quant=True
)

tokenizer = AutoTokenizer.from_pretrained(LORA_REPO, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL,
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True
)
model = PeftModel.from_pretrained(base_model, LORA_REPO)

# Clinical Prompting
findings = """
CTA CHEST: Large saddle pulmonary embolus straddling the bifurcation with RV/LV ratio of 1.4 and interventricular flattening.
"""

messages = [
    {"role": "system", "content": "You are an expert diagnostic radiologist. Generate a structured clinical IMPRESSION."},
    {"role": "user", "content": f"FINDINGS:\n{findings}"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=300, temperature=0.2)

print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
```

---

## 🎯 Clinical Benchmark Capabilities

1. **Findings-to-Impression Synthesis**: Condenses verbose imaging observations into clear, prioritized clinical impressions.
2. **Critical Findings & Urgent Alerts**: Highlights acute conditions (pulmonary embolism, large vessel occlusion, aortic dissection, tension pneumothorax, appendicitis).
3. **Structured Staging & Reporting**: Aligned with ACR Fleischner Society criteria, BI-RADS, LI-RADS, and PI-RADS reporting frameworks.

---

## 🔒 Clinical Disclaimer
*This model is released for research, clinical decision support benchmarking, and medical NLP exploration. It should not replace independent radiological interpretation by certified medical professionals.*