This 7B parameter vision-language model is designed to bring medical-grade multimodal intelligence into a smaller, more efficient package. The model not only understands medical text but also interprets visual information across scans, charts, diagrams, and structured documents. It can analyze X-rays, MRIs, pathology slides, medical diagrams, and even patient records containing forms, tables, or structured data. Compact yet powerful, the 7B model is optimized for efficiency while retaining the ability to summarize clinical information, answer contextual medical questions, and facilitate decision-making. It is particularly well-suited for scenarios that demand a balance of speed, accuracy, and multimodal understanding across both text and medical visuals. With 32K context window, it processes longer documents. Optimized for RAG applications, it integrates with healthcare databases and imaging systems to deliver informed responses across both visual and textual medical domains. Benchmarking Results: Achieves 71.0% average across OpenMed benchmarks Scores 75.85% on clinical knowledge assessment Reaches 81% on medical genetics understanding Performs at 84.72% for college biology concepts Processes professional medicine with 71.69% accuracy Handles medical MCQAs with 55.08% precision Maintains 59.07% accuracy on MedQA 4-options test Recommended Instance for this model is Standard_NC24ads_A100_v4.