richardyoung/llama-medx-v32

Llama-MedX v3.2 (GGUF)

Quantized build of the Llama-medx_v3.2 medical assistant model packaged for Ollama / llama.cpp runtimes. This export includes the Modelfile generated from the original Ollama registry entry and a GGUF binary derived from the upstream Hugging Face release.

• Base model: skumar9/Llama-medx_v3.2
• Architecture: Meta Llama 3.1 8B fine-tuned for medical QA

Variant

Variant	Size	Blob
latest	1.88 GB	sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff

Usage with Ollama

ollama create llama-medx-v32 -f modelfiles/llama-medx_v32--latest.Modelfile
ollama run llama-medx-v32

Source

Originally published on my Ollama profile: https://ollama.com/richardyoung/llama-medx_v32