Instructions to use osmosis-ai/osmosis-mcp-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osmosis-ai/osmosis-mcp-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="osmosis-ai/osmosis-mcp-4b",
	filename="osmosis-mcp-4B-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use osmosis-ai/osmosis-mcp-4b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf osmosis-ai/osmosis-mcp-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf osmosis-ai/osmosis-mcp-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf osmosis-ai/osmosis-mcp-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf osmosis-ai/osmosis-mcp-4b: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 osmosis-ai/osmosis-mcp-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf osmosis-ai/osmosis-mcp-4b: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 osmosis-ai/osmosis-mcp-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf osmosis-ai/osmosis-mcp-4b:Q4_K_M

Use Docker

docker model run hf.co/osmosis-ai/osmosis-mcp-4b:Q4_K_M

LM Studio
Jan
Ollama
How to use osmosis-ai/osmosis-mcp-4b with Ollama:
```
ollama run hf.co/osmosis-ai/osmosis-mcp-4b:Q4_K_M
```

Unsloth Studio

How to use osmosis-ai/osmosis-mcp-4b 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 osmosis-ai/osmosis-mcp-4b 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 osmosis-ai/osmosis-mcp-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for osmosis-ai/osmosis-mcp-4b to start chatting

How to use osmosis-ai/osmosis-mcp-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf osmosis-ai/osmosis-mcp-4b: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": "osmosis-ai/osmosis-mcp-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use osmosis-ai/osmosis-mcp-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf osmosis-ai/osmosis-mcp-4b: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 osmosis-ai/osmosis-mcp-4b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use osmosis-ai/osmosis-mcp-4b with Docker Model Runner:
```
docker model run hf.co/osmosis-ai/osmosis-mcp-4b:Q4_K_M
```

Lemonade

How to use osmosis-ai/osmosis-mcp-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull osmosis-ai/osmosis-mcp-4b:Q4_K_M

Run and chat with the model

lemonade run user.osmosis-mcp-4b-Q4_K_M

List all available models

lemonade list

Overview

Osmosis-MCP-4B is based on the Qwen3-4B model, fine-tuned with reinforcement learning to excel at multi step MCP-style tool usage.

We trained Osmosis-MCP-4B using a custom curriculum of multi-turn, tool-reliant prompts that mimic real-world use cases — for example:

"Given the weather in San Francisco, what are the top hiking locations?"

In addition, we provide a list of deterministic MCP like functions and mock server side behavior for the model to call and use.

This requires the model to reason through multiple tool invocations (e.g., weather → location ranker), and choose tools over intuition when applicable.

Training Approach

Our training pipeline leverages:

Dr. GRPO for stable and sample-efficient reinforcement learning.
Synthetic multi-step MCP interactions with strong tool chaining behavior, generated using our internal data engine.
SGLang + VeRL for efficient multi-turn rollout environments, built on top of Qwen3-4B for its function-calling capabilities.

Through this training methodology, we observed a notable behavioral shift: the model prefers invoking tools when appropriate, instead of relying solely on pre-trained intuition — a key milestone for MCP-native agents.

Why This Matters

MCP is fast becoming the open standard for tool-augmented AI agents. However:

Most top-performing models (e.g., Claude 3.7 Sonnet, Gemini 2.5 Pro) are closed.
Tool sprawl across clients and servers creates complexity.
Open models often lack the training to effectively use tools at all.

Osmosis-MCP-4B addresses all three — it’s small, powerful, and practical.