AshutoshHug47/llama3.2-1b-cybersec-GGUF

Llama 3.2 1B CyberSec (GGUF)

This repository contains GGUF quantizations of a fine-tuned Llama 3.2 1B Instruct model specialized for cybersecurity and secure coding.

Available Quants

• FP16
• Q4_0
• Q4_1
• Q4_K_M (recommended)
• Q4_K_S
• Q5_0
• Q5_1
• Q5_K_M
• Q6_K

Usage (llama.cpp)

./llama-cli -m llama3.2-cybersec-Q4_K_M.gguf

Usage (Ollama)

ollama create llama3.2-cybersec -f Modelfile-llama3.2-cybersec-Q4_K_M
ollama run llama3.2-cybersec

Notes

• This is a derived model
• Base model: meta-llama/Llama-3.2-1B-Instruct
• GGUF format for local inference only