Overview
MadriMed 1.2 is the second compact multimodal medical vision-language model by Madrisight. Building upon madriMed-VL-2B, MadriMed 1.2 delivers significant performance leaps across medical image understanding (Radiology, Pathology, CT, MRI, X-Ray) and medical reasoning.
It Delivers robust clinical reasoning capabilities, drastically reducing hallucinations and diagnostic contradictions while setting a new state-of-the-art benchmark for 2B medical vision models.
What's New in MadriMed 1.2?
- Massive Diagnostic Accuracy Gains:
- Massive jump on VQA-RAD overall score and most of the other evalution benchmarks.
- Resistant to Generation Hallucinations:
- Substantially reduced token corruption, repetition and positive-bias tendencies observed in version one.
- Structured Formating:
- Trained with graduated correctness scoring and reasoning-integrity penalties to enforce structured.
Quick Start
Installation
pip install torch torchvision transformers
prompt = """Question: Examine the mammogram image shown above. Which of the following findings is most evident? Answer Choices:A. Well-circumscribed round mass with benign featuresB. Clustered microcalcifications within an area of irregular densityC. Fat-containing lesion consistent with lipomaD. Diffuse bilateral breast edema Follow this exact step-by-step reasoning structure. ### 1. Key Clinical FindingsExtract the patient's age, gender, main symptoms, duration, objective physical exam findings, and abnormal laboratory/imaging results from the provided question and the images. ### 2. Differential DiagnosisList 2-3 highly probable conditions based on the extracted findings. Briefly state why the current presentation fits. ### 3. Option Elimination Analyze each provided choice. Write one sentence explaining why it is either correct or incorrect based on clinical guidelines. ### 4. Conclusion & Final AnswerState the final diagnostic/management conclusion. ### 5. Final correct choiceProvide final single correct choice."""
Run the model directly
import torchfrom transformers import AutoProcessor, Qwen3VLForConditionalGenerationfrom PIL import Image MODEL_ID = "madrisight/madrimed1.2-VL-2B"device = "mps" if torch.backends.mps.is_available() else "cpu" model = Qwen3VLForConditionalGeneration.from_pretrained( MODEL_ID, device_map=device, dtype=torch.float32, trust_remote_code=True,).eval() processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True) # Multi-image inputimage_paths = ["images/MM-1-a.png", "images/MM-1-b.png"]images = [Image.open(path).convert("RGB") for path in image_paths] # Chat Message Payloadmessages = [ { "role": "system", "content": "You are an expert clinical medical educator and USMLE board reviewer.", }, { "role": "user", "content": [{"type": "image"} for _ in images] + [{"type": "text", "text": prompt}] }] # Tokenize, Process, and Generatewith torch.inference_mode(): text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = processor( text=text, images=images, # Pass the flat list of PIL Image objects return_tensors="pt", padding=True, truncation=True, ).to(device) generated_ids = model.generate( **inputs, max_new_tokens=1024, do_sample=False, ) output_text = processor.batch_decode( generated_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True )[0].strip()
Output
### 1. Key Clinical Findings- **Patient's age and gender**: Not explicitly mentioned, but mammograms are typically used for women.- **Main symptoms**: Not specified, but mammograms are often performed for breast abnormalities.- **Duration**: Not specified, but mammograms are usually performed at the time of suspicion.- **Objective physical exam findings**: Not specified, but mammograms are used to detect abnormalities.- **Abnormal laboratory/imaging results**: Not specified, but mammograms are used to detect breast abnormalities.### 2. Differential Diagnosis- **Well-circumscribed round mass with benign features**: This could be a benign lesion such as a fibroadenoma.- **Clustered microcalcifications within an area of irregular density**: This could indicate a malignant process, such as ductal carcinoma in situ (DCIS) or invasive breast cancer.- **Fat-containing lesion consistent with lipoma**: This is a benign lesion and could be a lipoma.### 3. Option Elimination- **Well-circumscribed round mass with benign features**: This is a plausible finding, but it is less likely to be the primary concern in a mammogram without additional symptoms or findings.- **Clustered microcalcifications within an area of irregular density**: This is a highly suspicious finding for malignancy, as it is often associated with breast cancer.- **Fat-containing lesion consistent with lipoma**: This is a benign finding and less likely to be the primary concern in a mammogram without additional symptoms or findings.### 4. Conclusion & Final AnswerThe mammogram findings are most indicative of a malignant process, specifically breast cancer, due to the presence of clustered microcalcifications within an area of irregular density.### 5. Final correct choiceB. Clustered microcalcifications within an area of irregular density
Benchmark Results
MadriMed 1.2 was rigorously evaluated across 7 medical image and text benchmarks.
🔬 Multimodal & Visual Question Answering
Table with columns: Benchmark, MediX-R1 (2B), Qwen3.5-2B-MedVL (OpenMed), MadriMed 1.2 (2B)| Benchmark | MediX-R1 (2B) | Qwen3.5-2B-MedVL (OpenMed) | MadriMed 1.2 (2B) |
|---|
| VQA-RAD | 53.9% | 55.21% | 64.30% |
| PathVQA | 42.8% | 47.48% | 48.29% |
| SLAKE (Radiology) | 65.4% | 68.80% | 69.36% |
VQA Comparison with 4B
Table with columns: Benchmark, Metric, MediX-R1 2B, Qwen3.5-2B-MedVL, MedMO-4B-Next, MedGemma 1.5 4B, MedGemma 4B, MadriMed 1.2 2B| Benchmark | Metric | MediX-R1 2B | Qwen3.5-2B-MedVL | MedMO-4B-Next | MedGemma 1.5 4B | MedGemma 4B | MadriMed 1.2 2B |
|---|
| SLAKE | Overall | 65.40% | 68.80% | 74.00% | 59.80% Tok-F1 | 72.30% Tok-F1 | 69.36% |
| ↳ Closed | Accuracy | 68.40% | N/R |
Table with columns: Benchmark, Metric, MedMO-4B-Next, MedGemma (4B), MadriMed-VL-2B (v1), MadriMed 1.2 (2B)| Benchmark | Metric | MedMO-4B-Next | MedGemma (4B) | MadriMed-VL-2B (v1) | MadriMed 1.2 (2B) |
|---|
| MedXpertQA (Multimodal) | Accuracy | 27.0% | 24.43% | 21.50% | 23.50% |
| MedXpertQA (Text) | Accuracy | 16.5% | 14.2% | 11.02% | 13.55% |
📝 Text only Benchmarks
Table with columns: Benchmark, MedGemma 1.5 (4B), MedGemma (4B), MediX-R1 (2B), MadriMed 1.2 (2B)| Benchmark | MedGemma 1.5 (4B) | MedGemma (4B) | MediX-R1 (2B) | MadriMed 1.2 (2B) |
|---|
| PubMedQA | 68.2% | 73.4% | 47.2% | 66.6% |
| MedMCQA | 55.7% | 59.8% | 49.2% | 43.1% |
| MedQA-4opts | 69.1% | 64.4% | 49.7% | 41.56% |
Table with columns: Category, EM, Total VQA| Category | EM | Total VQA |
|---|
| Abnormality | 40.4% | 52 |
| Color | 81.8% | 33 |
| KG | 57.8% | 109 |
| Modality | 91.8% | 85 |
| Organ | 71.7% | 99 |
| Plane | 90.9% | 33 |
Medmcqa (Text-Only) Per-Category Performance
By Choice Type
Table with columns: Choice Type, Accuracy, Correct / Total| Choice Type | Accuracy | Correct / Total |
|---|
| Multi | 41.62% | 569 / 1,367 |
| Single | 43.82% | 1,234 / 2,816 |
By Subject
Table with columns: Subject, Accuracy, Correct / Total| Subject | Accuracy | Correct / Total |
|---|
| Anaesthesia | 41.18% | 14 / 34 |
| Anatomy | 44.02% | 103 / 234 |
| Biochemistry | 50.29% | 86 / 171 |
| Dental | 39.83% | 525 / 1,318 |
| ENT | 32.08% | 17 / 53 |
| Forensic Medicine | 37.31% |
Evaluation NoteBook
Technical Specifications
Table with columns: Component, Details| Component | Details |
|---|
| Base Architecture | Qwen/Qwen3-VL-2B-Thinking |
| Context & Vision | Native multimodal support with Dynamic M-RoPE |
| Dataset | mint-medmax/medmax_data and synthetic data |
| Precision | Native float32 |
| Training Platform | Apple Silicon chip |
| Training Framework | with custom fused kernels |
Benchmark Dataset Citations
- SLAKE:
BoKelvin/SLAKE
- MedXpertQA:
TsinghuaC3I/MedXpertQA
- VQA-RAD:
flaviagiammarino/vqa-rad
- PubMedQA:
qiaojin/PubMedQA
- MedQA (USMLE):
GBaker/MedQA-USMLE-4-options
Limitations & Safety Guidelines
Research & Educational Use Only
MadriMed 1.2 is an experimental research model. It is not certified for autonomous clinical diagnostic decision-making.
No Treatment Prescriptions
The model should not be used as an authoritative source for:
- Pharmaceutical dosages
- Surgical interventions
- Direct treatment pathways
- Other high-stakes clinical decisions
All model-generated interpretations, medical reasoning, and visual inferences should be reviewed and independently confirmed by a qualified, licensed medical professional before being used in a clinical context.
Citation
@software{madrimed1.2-VL-2B, title = {MadriMed 1.2: Advanced Multimodal Medical Reasoning at the 2B Scale}, author = {Madrisight}, year = {2026}, url = {https://huggingface.co/madrisight/madrimed1.2-VL-2B}}