Instructions to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RJ000/Mellum2-12B-A2.5B-Thinking-GGUF",
	filename="Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RJ000/Mellum2-12B-A2.5B-Thinking-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": "RJ000/Mellum2-12B-A2.5B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M

Ollama
How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with Ollama:
```
ollama run hf.co/RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
```

Unsloth Studio

How to use RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RJ000/Mellum2-12B-A2.5B-Thinking-GGUF to start chatting

How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RJ000/Mellum2-12B-A2.5B-Thinking-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": "RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-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 RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use RJ000/Mellum2-12B-A2.5B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RJ000/Mellum2-12B-A2.5B-Thinking-GGUF:Q4_K_M

Run and chat with the model

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

List all available models

lemonade list

Mellum2-12B-A2.5B-Thinking GGUF (Q4_K_M)

Quantized GGUF version of JetBrains/Mellum2-12B-A2.5B-Thinking for use with llama.cpp.

⚠️ Requires llama.cpp with Mellum architecture support. This is not yet in mainline llama.cpp — use PR #23966 or a build that includes it.

Model Details

Property	Value
Base model	JetBrains/Mellum2-12B-A2.5B-Thinking
Architecture	Mellum (MoE)
Total parameters	12B
Active parameters	2.5B
Experts	64 (8 per token)
Context length	128K (sliding window)
Quantization	Q4_K_M
File size	~7.5 GB

Usage

llama-server \
  -m Mellum2-12B-A2.5B-Thinking-Q4_K_M.gguf \
  -c 32000 \
  -ngl 99 \
  --jinja \
  --flash-attn on \
  --cache-type-k q4_0 \
  --cache-type-v q4_0 \
  --port 18081

For thinking mode, use reasoning_budget to cap reasoning tokens:

curl http://localhost:18081/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"Mellum2-12B-A2.5B-Thinking-Q4_K_M","messages":[{"role":"user","content":"Explain quicksort"}],"max_tokens":500,"reasoning_budget":512}'

Low VRAM (6GB GPU)

For GPUs with limited VRAM, offload MoE experts to CPU:

llama-server \
  -m Mellum2-12B-A2.5B-Thinking-Q4_K_M.gguf \
  -c 32000 \
  -ngl 99 \
  -ncmoe 20 \
  -t 8 \
  --jinja \
  --flash-attn on \
  --cache-type-k q4_0 \
  --cache-type-v q4_0

Tested on GTX 1060 6GB: ~18 t/s with ncmoe=20, ~22 t/s with ncmoe=10.

Acknowledgements

JetBrains for the original Mellum2 model
llama.cpp for the inference engine

Downloads last month: 1,586

GGUF

Model size

12B params

Architecture

mellum

Hardware compatibility

4-bit

Model tree for RJ000/Mellum2-12B-A2.5B-Thinking-GGUF

Base model

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

Quantized

(25)

this model