Instructions to use devehz/MagenticBrain-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 devehz/MagenticBrain-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 devehz/MagenticBrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf devehz/MagenticBrain-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 devehz/MagenticBrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf devehz/MagenticBrain-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 devehz/MagenticBrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf devehz/MagenticBrain-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 devehz/MagenticBrain-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf devehz/MagenticBrain-GGUF:Q4_K_M

Use Docker

docker model run hf.co/devehz/MagenticBrain-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use devehz/MagenticBrain-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/devehz/MagenticBrain-GGUF:Q4_K_M

Ollama
How to use devehz/MagenticBrain-GGUF with Ollama:
```
ollama run hf.co/devehz/MagenticBrain-GGUF:Q4_K_M
```

Unsloth Studio

How to use devehz/MagenticBrain-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devehz/MagenticBrain-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devehz/MagenticBrain-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devehz/MagenticBrain-GGUF to start chatting

How to use devehz/MagenticBrain-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devehz/MagenticBrain-GGUF:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use devehz/MagenticBrain-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devehz/MagenticBrain-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 "devehz/MagenticBrain-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"

Docker Model Runner
How to use devehz/MagenticBrain-GGUF with Docker Model Runner:
```
docker model run hf.co/devehz/MagenticBrain-GGUF:Q4_K_M
```

Lemonade

How to use devehz/MagenticBrain-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devehz/MagenticBrain-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MagenticBrain-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use devehz/MagenticBrain-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 devehz/MagenticBrain-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 devehz/MagenticBrain-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

MagenticBrain-GGUF

GGUF quantization of microsoft/MagenticBrain (14B) for use with llama.cpp and compatible runners (Lemonade, LM Studio, Ollama, etc.).

Available quants

File	Quant	Size	Notes
`MB-Q6_K.gguf`	Q6_K	~11.5 GB	Recommended — near-lossless; preserves the model's structured tool-call / JSON fidelity
`MB-Q4_K_M.gguf`	Q4_K_M	~9 GB	Fallback for tight VRAM budgets

Converted with convert_hf_to_gguf.py (BF16 intermediate) and quantized with llama-quantize from llama.cpp. Standard k-quants, no imatrix calibration.

About the model

MagenticBrain is Microsoft Research AI Frontiers' 14B orchestration model, SFT'd from Qwen3-14B on agentic data — function calling (APIGen-MT, ToolACE, xLAM), 250+ synthetic MCP environments, file-system and terminal trajectories, and sub-agent delegation traces (handoffs to Fara1.5-9B) — followed by an RL stage on terminal tasks. It plans multi-step tasks, calls declared tools via structured JSON (never inventing new ones), coordinates sub-agents, and follows a submit-to-terminate protocol.

This is an orchestration-first model, not a general-purpose chat model. It is co-designed with, and most thoroughly evaluated in, Magentic-Lite (Magentic-UI v0.2).

Recommended settings

Context: up to 32K
Thinking: disabled by default (enable_thinking: false) — keep it off; verbose reasoning degrades long agentic trajectories
Tool calling: schemas are injected by the harness; the model expects to select only from declared tools

Usage

llama.cpp:

llama-server -m MB-Q6_K.gguf -ngl 99 -c 32768

Lemonade / LM Studio / Ollama: register the GGUF file directly or pull this repo through the app's model management.

License & credit

MIT — same as the base model. All credit to Microsoft Research AI Frontiers. This repo is a community quantization and is not affiliated with or endorsed by Microsoft. See the base model card for full details.