Instructions to use Taimwe/securecoder-30b-pro-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Taimwe/securecoder-30b-pro-GGUF with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Taimwe/securecoder-30b-pro-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Taimwe/securecoder-30b-pro-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Taimwe/securecoder-30b-pro-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Taimwe/securecoder-30b-pro-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Ollama
How to use Taimwe/securecoder-30b-pro-GGUF with Ollama:
```
ollama run hf.co/Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Taimwe/securecoder-30b-pro-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Taimwe/securecoder-30b-pro-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Taimwe/securecoder-30b-pro-GGUF with Docker Model Runner:
```
docker model run hf.co/Taimwe/securecoder-30b-pro-GGUF:Q4_K_M
```

Lemonade

How to use Taimwe/securecoder-30b-pro-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.securecoder-30b-pro-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Taimwe/securecoder-30b-pro-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Taimwe/securecoder-30b-pro-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Taimwe/securecoder-30b-pro-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Taimwe/securecoder-30b-pro-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

SecureCoder (GGUF Q4_K_M)

Q4_K_M GGUF export of Taimwe/securecoder-30b-pro-merged, a QLoRA fine-tune of unsloth/Qwen3-Coder-30B-A3B-Instruct for code, tool calling and cybersecurity.

For the LoRA adapter, full eval numbers, training data, and limitations, see Taimwe/securecoder-30b-pro.

Files

File	Notes
`model-Q4_K_M.gguf`	Q4_K_M quantisation (~7 GB)
`README.md`	this card

Quick run

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

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

# LM Studio — drag the gguf into the UI

Tool-calling is via Qwen3-Coder's native chat template; pass tools=[…] as a list of OpenAI-style function schemas.

Measured numbers (from `securecoder-30b-pro/eval-report.json`)

Tool-call parse rate (60 prompts): 100.0%
Tool-call correct function: 100.0%
Tool-call schema-conformant arguments: 98.3% (59/60)
Code sanity AST+compile (15 prompts): 6.7% (1/15) — see limitations

Limitations

No safety training. The training mix contains recon/enumeration material; the base model has no alignment layer; the fine-tune adds none. Use the outputs with care and review code before execution.
2k context window (inherited from the base).
Code generation on harder prompts is weak (6.7% AST-clean on the eval set).
The Q4_K_M quantisation is lossy compared to the 16-bit merge. For best tool calling fidelity, use the merged safetensors repo instead.

Downloads last month: 55

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

4-bit

Model tree for Taimwe/securecoder-30b-pro-GGUF

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Finetuned

unsloth/Qwen3-Coder-30B-A3B-Instruct

Adapter

Taimwe/securecoder-30b-pro

Adapter

(1)

this model

SecureCoder (GGUF Q4_K_M)

Files

Quick run

Measured numbers (from securecoder-30b-pro/eval-report.json)

Limitations

Model tree for Taimwe/securecoder-30b-pro-GGUF

Measured numbers (from `securecoder-30b-pro/eval-report.json`)