MedQA clinical AI fine-tuned on AMD MI300X using ROCm
a new clinical ai model was fine-tuned entirely on amd hardware using rocm, proving the huggingface ecosystem works without cuda. the qwen3-1.7b based model trained on 2,000 samples in 5 minutes.
A project named MedQA successfully fine-tuned a clinical question-answering model using only AMD hardware and the ROCm software stack. Built on a single AMD Instinct MI300X with 192 GB of HBM3 memory, the pipeline fine-tuned Qwen3-1.7B using LoRA without any CUDA dependencies or code changes. Training on 2,000 MedMCQA samples took approximately 5 minutes, utilizing full fp16 precision to avoid quantization. The resulting model generates answers and clinical explanations for medical multiple-choice questions, validating that the HuggingFace ecosystem—including Transformers, PEFT, and TRL—operates seamlessly on ROCm.