alaabh/llama3.1-deepseek-r1-medical-merged-16bit-GGUF

Llama 3.1 DeepSeek R1 Medical - GGUF

This is a GGUF conversion of alaabh/llama3.1-deepseek-r1-medical-merged-16bit.

Model Details

• Format: GGUF
• Precision: F16
• Size: ~10.6GB
• Compatible with: llama.cpp, Ollama, LM Studio, and other GGUF-supported inference engines

Usage

With llama.cpp:

./llama-cli -m model.gguf -p "What is hypertension?" -n 100

With Ollama:

# Create Modelfile
echo 'FROM ./model.gguf' > Modelfile
ollama create medical-llama -f Modelfile
ollama run medical-llama

Original Model

This GGUF conversion is based on the merged 16-bit model that combines Llama 3.1 with DeepSeek R1 for medical applications.