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

Libraries

How to use Mungert/Mellum2-12B-A2.5B-Instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Mungert/Mellum2-12B-A2.5B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mungert/Mellum2-12B-A2.5B-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mungert/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 Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mungert/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 Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mungert/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 Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mungert/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 Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use Mungert/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 "Mungert/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": "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Mungert/Mellum2-12B-A2.5B-Instruct-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Unsloth Studio

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

How to use Mungert/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 Mungert/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": "Mungert/Mellum2-12B-A2.5B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mungert/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

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Mungert/Mellum2-12B-A2.5B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

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

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

Model Generation Details

This model was generated using llama.cpp at commit 263cc04a5.

Click here to get info on choosing the right GGUF model format

Mellum2 Instruct

Use this model when you want direct, low-latency answers without an explicit chain of thought — interactive chat, code assistance, tool use, and instruction following. If you need explicit reasoning before the answer (complex debugging, planning, multi-step agentic flows), use Thinking instead.

Mellum2 Instruct Highlights

Mellum2 Instruct is a post-trained assistant model trained by JetBrains.

The model uses a Mixture-of-Experts architecture with 64 experts and activates 8 experts per token. It uses a combination of sliding-window and full attention layers, with a context length of 131,072 tokens.

It is produced from Mellum2-12B-A2.5B-Base by supervised fine-tuning followed by reinforcement learning with verifiable rewards (RLVR) on math, executable coding, tool use, instruction following, reasoning, and knowledge tasks. Mellum2 Instruct answers directly, without an externalized chain of thought.

Mellum2 Model Family

This repository contains one checkpoint from the Mellum2 family.

Checkpoint	Description
Base Pretrain	Base checkpoint before long-context extension
Base	Final base model
Instruct SFT	Supervised instruction-tuned checkpoint
Thinking SFT	Supervised thinking checkpoint
Instruct	RL-tuned instruction model
Thinking	RL-tuned thinking model

Model Overview

Mellum2 Instruct has the following features:

Number of Layers: 28
Hidden Size: 2304
Intermediate Size: 7168
MoE Intermediate Size: 896
Number of Experts: 64
Number of Activated Experts: 8
Number of Attention Heads (GQA): 32 for Q and 4 for KV
Context Length: 131,072
Sliding Window: 1,024
Vocabulary Size: 98,304
Precision: bfloat16

Serving with vLLM

# Without tool calling
vllm serve JetBrains/Mellum2-12B-A2.5B-Instruct --max-model-len 131072

# With tool calling
vllm serve JetBrains/Mellum2-12B-A2.5B-Instruct \
  --max-model-len 131072 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

Quickstart

Text-Only Input

from openai import OpenAI
# Configured by environment variables
client = OpenAI()

messages = [
    {"role": "user", "content": "Write a Python function to reverse a string."},
]

chat_response = client.chat.completions.create(
    model="JetBrains/Mellum2-12B-A2.5B-Instruct",
    messages=messages,
    max_tokens=81920,
    temperature=0.6,
    top_p=0.95,
    extra_body={
        "top_k": 20,
    },
)
print("Chat response:", chat_response)

Evaluation

Post-training evaluation for the instruct (no-thinking) variants. All values are percentages; higher is better except HarmBench, where lower is better. All values self-reported by JetBrains.

Benchmark	Mellum2 Instruct SFT	Mellum2 Instruct	Qwen3.5 (4B)	Qwen3.5 (9B)	OLMo-3 (7B)	Ministral 3 (14B)	Seed-Coder (8B)
Coding
LiveCodeBench v6	30.9	37.2	51.0	63.7	28.2	42.4	28.1
EvalPlus	76.2	78.4	69.4	71.8	67.3	74.1	73.8
MultiPL-E	64.6	67.1	51.0	67.1	36.1	71.5	77.0
Tool Use
BFCL v4	31.8	44.2	52.0	60.6	19.8	38.8	—
BFCL v3	43.1	66.3	64.1	70.5	41.9	52.7	—
Math
AIME	29.9	41.7	38.3	58.3	40.0	33.3	0.0
GSM-Plus	73.0	80.5	85.2	87.9	85.8	86.6	50.4
Knowledge
MMLU-Redux	77.4	78.1	87.5	91.1	71.8	85.9	38.1
GPQA Diamond	38.9	40.9	76.8	79.8	40.9	58.6	20.2
Conversational
IFEval	69.3	75.8	82.1	83.9	83.2	67.3	56.2
JetBrains pairwise	66.7	68.1	60.6	77.8	44.4	72.4	43.0
MixEval	62.9	62.2	65.9	71.1	59.4	71.2	37.2
BS-Bench	24.0	18.0	56.9	61.0	22.0	9.0	5.0
Safety
HarmBench (↓)	8.4	23.1	20.3	20.9	14.7	56.5	40.0
XSTest	78.3	81.2	93.2	91.2	91.2	96.8	86.3

Notes:

EvalPlus is the mean of HumanEval+ and MBPP+.
AIME is the mean of AIME 2025 and AIME 2026 (30 questions each).
BFCL v4 is the macro-average of five subtasks: v1, v2, v3, web search, memory.
JetBrains pairwise is win rate against Qwen2.5-7B-Instruct on an internal benchmark.
— indicates the model lacks native tool calling.

For more details, see the Mellum2 Technical Report.

License

Released under the Apache 2.0 license.

🚀 If you find these models useful

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

TurboLLM (GPT-4.1-mini)
HugLLM (Hugginface Open-source models)
TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

Function calling against live network services
How small can a model go while still handling:
- Automated Nmap security scans
- Quantum-readiness checks
- Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

✅ Zero-configuration setup
⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

**It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
Create custom cmd processors to run .net code on Quantum Network Monitor Agents
Real-time network diagnostics and monitoring
Security Audits
Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a comprehensive security audit on my server"
'"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊

Downloads last month: 272

GGUF

Model size

12B params

Architecture

mellum

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

View +1 variant

Collection including Mungert/Mellum2-12B-A2.5B-Instruct-GGUF

Function Calling Models

Collection

Models that specialize in function calling • 12 items • Updated Jun 14 • 4

Paper for Mungert/Mellum2-12B-A2.5B-Instruct-GGUF

Mellum2 Technical Report

Paper • 2605.31268 • Published May 29 • 59

Evaluation results

pass@1 on LiveCodeBench v6
self-reported

37.200
pass@1 on EvalPlus (HumanEval+ / MBPP+ mean)
self-reported

78.400
pass@1 on MultiPL-E (7 languages)
self-reported

67.100
accuracy on BFCL v3
self-reported

66.300
accuracy on BFCL v4 (macro-avg of 5 subtasks)
self-reported

44.200
exact match on AIME 2025+2026 (mean, 30 questions each)
self-reported

41.700
exact match on GSM-Plus
self-reported

80.500
accuracy on MMLU-Redux
self-reported

78.100