Instructions to use katali13/Sous-Chef-27B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf katali13/Sous-Chef-27B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/katali13/Sous-Chef-27B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use katali13/Sous-Chef-27B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "katali13/Sous-Chef-27B-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": "katali13/Sous-Chef-27B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/katali13/Sous-Chef-27B-GGUF:Q4_K_M

Ollama
How to use katali13/Sous-Chef-27B-GGUF with Ollama:
```
ollama run hf.co/katali13/Sous-Chef-27B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use katali13/Sous-Chef-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf katali13/Sous-Chef-27B-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": "katali13/Sous-Chef-27B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use katali13/Sous-Chef-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/katali13/Sous-Chef-27B-GGUF:Q4_K_M
```

Lemonade

How to use katali13/Sous-Chef-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull katali13/Sous-Chef-27B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Sous-Chef-27B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-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 katali13/Sous-Chef-27B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use katali13/Sous-Chef-27B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf katali13/Sous-Chef-27B-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 "katali13/Sous-Chef-27B-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"

Sous Chef 27B (GGUF)

The local model behind Bakery, a local-LLM security and reverse-engineering agent platform for VS Code, created by Ancil Chandler.

Sous Chef is tuned for the work Bakery does: reading unfamiliar codebases, static analysis and vulnerability hunting, driving Ghidra for binary reverse engineering, sandboxed dynamic analysis, and running autonomously across many tool-calling steps.

Files

Quant	Size	Notes
`Sous-Chef-27B-MTP.gguf`	5.9 GB
`Sous-Chef-27B-Q4_K_M.gguf`	16.8 GB
`Sous-Chef-27B-Q8_0.gguf`	29.0 GB
`mmproj-Sous-Chef-27B-F16.gguf`	0.9 GB

The vision tower ships as mmproj-*.gguf - pass it with --mmproj to use images. The NextN speculative-decoding draft head ships as *-MTP.gguf.

Licence

Derived from an open-weights 27B base model licensed under Apache-2.0, then finetuned by Ancil Chandler for the Bakery project. The weights have been modified from the original. The Apache-2.0 licence and its attribution requirements carry through to this repository, and a copy of LICENSE is included here.

Apache-2.0 grants no trademark rights, so this model ships under its own name and is not affiliated with, sponsored by, or endorsed by any upstream vendor.

Note on behaviour

This checkpoint derives from an abliterated base and does not carry the refusal behaviour of the original instruct model. It will attempt most requests. Use it accordingly, and keep it behind whatever controls your context requires.

Downloads last month: 322

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

View +1 variant