Instructions to use Tekimax/granite-ml-coder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tekimax/granite-ml-coder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Tekimax/granite-ml-coder-GGUF",
	filename="granite-ml-coder-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Tekimax/granite-ml-coder-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tekimax/granite-ml-coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tekimax/granite-ml-coder-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tekimax/granite-ml-coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tekimax/granite-ml-coder-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 Tekimax/granite-ml-coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Tekimax/granite-ml-coder-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 Tekimax/granite-ml-coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tekimax/granite-ml-coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Tekimax/granite-ml-coder-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Tekimax/granite-ml-coder-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tekimax/granite-ml-coder-GGUF:Q4_K_M

Ollama
How to use Tekimax/granite-ml-coder-GGUF with Ollama:
```
ollama run hf.co/Tekimax/granite-ml-coder-GGUF:Q4_K_M
```

Unsloth Studio

How to use Tekimax/granite-ml-coder-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 Tekimax/granite-ml-coder-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 Tekimax/granite-ml-coder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use Tekimax/granite-ml-coder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tekimax/granite-ml-coder-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": "Tekimax/granite-ml-coder-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Tekimax/granite-ml-coder-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tekimax/granite-ml-coder-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 Tekimax/granite-ml-coder-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Tekimax/granite-ml-coder-GGUF with Docker Model Runner:
```
docker model run hf.co/Tekimax/granite-ml-coder-GGUF:Q4_K_M
```

Lemonade

How to use Tekimax/granite-ml-coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tekimax/granite-ml-coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-ml-coder-GGUF-Q4_K_M

List all available models

lemonade list

granite-ml-coder-GGUF

GGUF builds of Tekimax/granite-ml-coder — a compact Python / machine-learning coding assistant fine-tuned from ibm-granite/granite-3.1-1b-a400m-instruct. These run on CPU and Apple Silicon (Metal) via llama.cpp, Ollama, and LM Studio.

Files

File	Bits	Size	Notes
`granite-ml-coder-Q4_K_M.gguf`	4-bit	~378 MB	recommended — loads fast, near-full quality

Run it

Ollama (from the public registry)

ollama run tekimaxllc/granite-ml-coder "Write a sklearn pipeline for the iris dataset"

Ollama (from this GGUF directly)

ollama run hf.co/Tekimax/granite-ml-coder-GGUF

llama.cpp

llama-cli -m granite-ml-coder-Q4_K_M.gguf \
  -p "Write a Keras autoencoder for network-traffic anomaly detection"

LM Studio

Search for Tekimax/granite-ml-coder-GGUF, download the Q4_K_M file, and chat.

Suggested system prompt

You are an expert Python machine-learning engineer. Write correct, runnable code,
explain each pipeline step, watch for overfitting and how gradient descent
converges, and recommend the best model or formula for the task.

Intended use & limitations

Good for drafting Python ML code (scikit-learn, pandas, NumPy, Keras) and explaining ML concepts, fully offline. It's a 1B model — treat output as a fast first draft and verify before use. See the full model card for training details and limitations.

License

Apache-2.0 (inherited from ibm-granite/granite-3.1-1b-a400m-instruct).

Downloads last month: 69

GGUF

Model size

1B params

Architecture

granitemoe

Hardware compatibility

4-bit

Model tree for Tekimax/granite-ml-coder-GGUF

Base model

ibm-granite/granite-3.1-1b-a400m-base

Finetuned

ibm-granite/granite-3.1-1b-a400m-instruct

Finetuned

Tekimax/granite-ml-coder

Quantized

(1)

this model

Tekimax
/

granite-ml-coder-GGUF

granite-ml-coder-GGUF

Files

Run it

Ollama (from the public registry)

Ollama (from this GGUF directly)

llama.cpp

LM Studio

Suggested system prompt

Intended use & limitations

License

Model tree for Tekimax/granite-ml-coder-GGUF

Space using Tekimax/granite-ml-coder-GGUF 1