Instructions to use MadlabOSS/LFM2-2.6B-SDG-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MadlabOSS/LFM2-2.6B-SDG-GGUF",
	filename="LFM2-2.6B-SDG-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

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 MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

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 MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

Use Docker

docker model run hf.co/MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

LM Studio
Jan
Ollama
How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with Ollama:
```
ollama run hf.co/MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
```

Unsloth Studio new

How to use MadlabOSS/LFM2-2.6B-SDG-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 MadlabOSS/LFM2-2.6B-SDG-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 MadlabOSS/LFM2-2.6B-SDG-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MadlabOSS/LFM2-2.6B-SDG-GGUF to start chatting

Pi new

How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

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": "MadlabOSS/LFM2-2.6B-SDG-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MadlabOSS/LFM2-2.6B-SDG-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 MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

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 MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with Docker Model Runner:
```
docker model run hf.co/MadlabOSS/LFM2-2.6B-SDG-GGUF:F16
```

Lemonade

How to use MadlabOSS/LFM2-2.6B-SDG-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MadlabOSS/LFM2-2.6B-SDG-GGUF:F16

Run and chat with the model

lemonade run user.LFM2-2.6B-SDG-GGUF-F16

List all available models

lemonade list

Madlab Synthetic Data Generator

🧠 Overview

The Madlab SDG 2.6B is part of the MadlabOSS Synthetic Data Generator family — a suite of small, efficient synthetic data generators designed for rule‑consistent, semantically coherent variation.
This model was trained on a closed-source dataset created through a multi-stage synthetic data generation process using a modified Madlab training pipeline.

🚀 Intended Use

This model is optimized for:

Madlab synthetic data generation

It is not intended as a general-purpose chatbot.

🧩 Model Details

Base Model: LFM2-2.6B
Parameter Count: 2.6 Billion
Training Type: Supervised fine-tuning
Sequence Length: 1024
Precision: FP16
Framework: PyTorch / Transformers

📦 Training Data

The model was trained on:

1444 compressed and encoded dataset pairs
High variation in output
Preservation of semantic meaning
Data entirely generated with Madlab

🏋️ Training Procedure

Hyperparameters

Epochs: 6
Batch size: 48
Learning rate: cosine schedule, peak ~4e-5
Optimizer: AdamW
Gradient clipping: 1.0
Gradient accumulation: 1

Hardware

Training was performed on:

RTX 6000 Blackwell (96GB)

📊 Evaluation

Synthetic Data Expansion Benchmark

A curated set of 30 input/target pairs was programmatically expanded using a Python script.
Metrics include seed pairs covered, total variation count, and semantic quality.
The task is to generate 5 variations of each incoming pair.

Run	Model	Semantic Quality	Variations	Seeds Covered	Efficiency (Variations/Param)	Dataset
1	LFM2-350M-16	6.5	94	23	268.57	Madlab sdg small
2	LFM2-350M-16	3.5	46	11	131.43	base model
3	LFM2-350M-f16	6.5	97	22	277.14	Madlab sdg small
4	Qwen3-coder-30B-instruct-q8	8.2	149	26	4.97	base model
5	LFM2-350M-f16	7.5	136	21	388.57	Madlab sdg medium
6	LFM2-2.6B-f16	9.0	137	25	52.69	Madlab sdg medium
7	LFM2-2.6B-f16	9.9	180	25	69.23	Madlab sdg large
8	LFM2-2.6B-f16	6.2	157	20	60.38	Madlab sdg test
9	LFM2-2.6B-f16	10.0	248	27	95.38	Madlab sdg large
10	Qwen3-235B-q3-k_m	9.5	150	27	0.64	base model
11	LFM2.5-1.2B-instruct-f16	9.1	244	30	203.33	Madlab sdg large

Qualitative Behavior

Overperforms in variation count
Maintains strict semantic correctness

🔒 Safety

This model is a synthetic data generator. It is not designed for conversational use and is not suitable for anything other than generating synthetic datasets.

It is not designed for: