Instructions to use koshuro/lfm2-1.2b-claude-opus-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use koshuro/lfm2-1.2b-claude-opus-distill with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="koshuro/lfm2-1.2b-claude-opus-distill",
	filename="lfm2-1.2b.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use koshuro/lfm2-1.2b-claude-opus-distill 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 koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf koshuro/lfm2-1.2b-claude-opus-distill: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 koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf koshuro/lfm2-1.2b-claude-opus-distill: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 koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M

Use Docker

docker model run hf.co/koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M

LM Studio
Jan
Ollama
How to use koshuro/lfm2-1.2b-claude-opus-distill with Ollama:
```
ollama run hf.co/koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
```

Unsloth Studio

How to use koshuro/lfm2-1.2b-claude-opus-distill 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 koshuro/lfm2-1.2b-claude-opus-distill 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 koshuro/lfm2-1.2b-claude-opus-distill to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for koshuro/lfm2-1.2b-claude-opus-distill to start chatting

Atomic Chat new
Docker Model Runner
How to use koshuro/lfm2-1.2b-claude-opus-distill with Docker Model Runner:
```
docker model run hf.co/koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M
```

Lemonade

How to use koshuro/lfm2-1.2b-claude-opus-distill with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull koshuro/lfm2-1.2b-claude-opus-distill:Q4_K_M

Run and chat with the model

lemonade run user.lfm2-1.2b-claude-opus-distill-Q4_K_M

List all available models

lemonade list

Model Card for Model ID

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency. This model has been fine tuned using claude opus 4.6 reasoning traces, improving its coding and responce formatting abilities.

Model Sources

Repository: [https://huggingface.co/LiquidAI/LFM2-1.2B]

Uses

They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations. However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.

Downloads last month: 95

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support