Used code:
https://github.com/FiveTechSoft/tinyMedical
Trained model:
https://huggingface.co/fivetech/tinyMedical-GGUF/tree/main
used engine to run the resulting GGUF file:
https://github.com/ggerganov/llama.cpp
You can also use LM Studio to use the GGUF files:
https://lmstudio.ai/