Instructions to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="junwatu/Mellum2-12B-A2.5B-Instruct-GGUF",
	filename="Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junwatu/Mellum2-12B-A2.5B-Instruct-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": "junwatu/Mellum2-12B-A2.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

Ollama
How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with Ollama:
```
ollama run hf.co/junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for junwatu/Mellum2-12B-A2.5B-Instruct-GGUF to start chatting

How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf junwatu/Mellum2-12B-A2.5B-Instruct-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": "junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-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 junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use junwatu/Mellum2-12B-A2.5B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull junwatu/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mellum2-12B-A2.5B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Mellum2 12B A2.5B Instruct GGUF

This is a GGUF quantization of JetBrains/Mellum2-12B-A2.5B-Instruct.

Model

Mellum2 is a Mixture-of-Experts model from JetBrains.

Key details:

Total parameters: 12B
Active parameters per token: 2.5B
Architecture: MoE
Experts: 64
Active experts per token: 8
Context length: 131,072 tokens
License: Apache 2.0
Original model: JetBrains/Mellum2-12B-A2.5B-Instruct
Model collection: JetBrains Mellum 2

Quantization

Field	Value
File	`Mellum2-12B-A2.5B-Instruct-Q4_K_M.gguf`
Hugging Face file size	`8.1 GB`

The quantizer reported fallback quantization for 28 tensors. This happened because some Mellum2 expert tensors have width 896, which is not divisible by the block size required by some K-quant formats.

Practical meaning:

The model is labeled Q4_K_M.
Some tensors use fallback formats such as q5_0 or q8_0.
The final file is larger than a pure Q4 estimate.

Important Compatibility Warning

This GGUF requires a llama.cpp build with Mellum2 support.

This GGUF was converted and quantized with the Mellum2 PR branch below. If you use another llama.cpp build, verify that it includes Mellum2 support before loading the model.

Use the Mellum2 PR branch: Xarbirus/llama.cpp/tree/mellum2

Related upstream PR: ggml-org/llama.cpp#23966

Build a compatible llama.cpp:

git clone --branch mellum2 https://github.com/Xarbirus/llama.cpp
cd llama.cpp
cmake -B build
cmake --build build --config Release -j

Local Usage

Example:

./build/bin/llama-cli \
  -m ./Mellum2-12B-A2.5B-Instruct-Q4_K_M.gguf \
  -c 8192 \
  -ngl 99 \
  -p "Write a Python function that validates whether a string is a palindrome."

Runtime memory depends on context length, prompt size, backend, and machine memory. Adjust -c and -ngl for your hardware.

License

This GGUF quantization follows the base model license: Apache 2.0

Base model: JetBrains/Mellum2-12B-A2.5B-Instruct

Check the original model card for the full license terms before redistribution or production use.

Downloads last month: 524

GGUF

Model size

12B params

Architecture

mellum

Hardware compatibility

4-bit

Model tree for junwatu/Mellum2-12B-A2.5B-Instruct-GGUF

Base model

JetBrains/Mellum2-12B-A2.5B-Instruct

Quantized

(16)

this model

junwatu
/

Mellum2-12B-A2.5B-Instruct-GGUF