unsloth/medgemma-27b-it

The unsloth/medgemma-27b-it is a 27 billion parameter instruction-tuned text-only variant of Google's Gemma 3 model, specifically trained for medical text comprehension and reasoning. It features a 32768 token context length and is optimized for inference-time computation in medical reasoning tasks. This model excels at medical question answering and text-based tasks, outperforming base Gemma models on clinically relevant benchmarks.