Taimwe/securecoder-30b-pro-v3-GGUF

SecureCoder (GGUF Q4KM)

GGUF export of Taimwe/securecoder-30b-pro-merged, a LoRA fine-tune of unsloth/Qwen3-Coder-30B-A3B-Instruct for code + tool calling + cybersecurity (offence and defence).

Files

Usage (llama.cpp / Ollama / LM Studio)

# llama.cpp server
llama-server -m model-Q4_K_M.gguf --host 0.0.0.0 --port 8080 -ngl 99

# Ollama
ollama create securecoder -f Modelfile
ollama run securecoder "Write a binary search in Rust."

See the parent repo for full provenance, training data, and the limitations section.