Instructions to use LiquidAI/LFM2-2.6B-Exp-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="LiquidAI/LFM2-2.6B-Exp-GGUF", filename="LFM2-2.6B-Exp-F16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
Use Docker
docker model run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LiquidAI/LFM2-2.6B-Exp-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": "LiquidAI/LFM2-2.6B-Exp-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
- Ollama
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with Ollama:
ollama run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
- Unsloth Studio new
How to use LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for LiquidAI/LFM2-2.6B-Exp-GGUF to start chatting
- Pi new
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf LiquidAI/LFM2-2.6B-Exp-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": "LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-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 LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with Docker Model Runner:
docker model run hf.co/LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
- Lemonade
How to use LiquidAI/LFM2-2.6B-Exp-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LiquidAI/LFM2-2.6B-Exp-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.LFM2-2.6B-Exp-GGUF-Q4_K_M
List all available models
lemonade list
LFM Open License v1.0 isn't free license
Tthank you for the great work; however, the current LFM Open License v1.0 includes a revenue‑threshold clause that restricts commercial use for entities earning ≥ $10 M, which violates Freedom 0 (the freedom to run the program for any purpose) and OSI’s “no discrimination against fields of endeavour” rule, meaning the software is not free or open source—could you consider re‑licensing it under a recognized free‑software license such as MIT, BSD‑3‑Clause, Apache 2.0, or GPL‑3.0 (you can still monetize support or services via a separate commercial agreement)?
Thanks for the feedback. The $10M revenue threshold is an intentional design choice to keep the models freely accessible for most users while sustaining continued development through enterprise licensing.
Yeah, here we go again. Another outfit watering down the word "Open" until it means absolutely nothing. They slap "LFM Open License" on it like it's some noble contribution to the community, but it's got a built-in cash register that locks once you hit $10M. It's not open source; it's a freemium trial with extra steps—a demo version for everyone except the companies who could actually pay for the development they're supposedly trying to "sustain."
The whole "We need to fund development" line? Classic. They want all the goodwill, the hype, and the free labor from the open-source community—the testing, the PRs, the evangelism—but they don't want to actually play by the community's rules. They're happy to take from the ecosystem of collaboration, but they'll only give on their own restrictive, self-serving terms. It's not a license; it's a marketing tactic wrapped in open-washing. They want to look like heroes of open source while keeping the real keys in their pocket. Just call it what it is: a proprietary license with a very generous free tier. Don't insult everyone's intelligence by calling it "Open."