Instructions to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "F-urkan/LFM2-8B-A1B-Q4_K_M-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": "F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M

SGLang

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-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 "F-urkan/LFM2-8B-A1B-Q4_K_M-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": "F-urkan/LFM2-8B-A1B-Q4_K_M-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 "F-urkan/LFM2-8B-A1B-Q4_K_M-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": "F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF to start chatting

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf F-urkan/LFM2-8B-A1B-Q4_K_M-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": "F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf F-urkan/LFM2-8B-A1B-Q4_K_M-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 "F-urkan/LFM2-8B-A1B-Q4_K_M-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"

Docker Model Runner
How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2-8B-A1B-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-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 F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

LFM2-8B-A1B-Q4_K_M-GGUF

Just a copy of Q4_K_M version "LiquidAI/LFM2-8B-A1B-GGUF".

With User-Friendly simple commands.

Requirements:

linux or stable llama.cpp install with a version newer than 6709.
5 gb vram or ram (cpu is enough)
5 gb disk space

Step-by-step usage

Download Model

Option 1 (fast download speed): 120 mb/s

sudo apt install aria2 -y
aria2c -x 16 -s 16 -k 1M \
  "https://huggingface.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF/resolve/main/LFM2-8B-A1B-Q4_K_M.gguf" \
  -o LFM2-8B-A1B-Q4_K_M.gguf

Option 2 (slow but easy): 10 mb/s

wget https://huggingface.co/F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF/resolve/main/LFM2-8B-A1B-Q4_K_M.gguf

Option 3 (Depend on your browser):

Just click auto download link: link

Get llama.cpp

If your llama.cpp version is newer than b6709 you can skip.

With brew

Install brew:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" # if brew is installed you can skip.
export PATH="/home/linuxbrew/.linuxbrew/bin:$PATH"

Install llama.cpp:

brew install llama.cpp

Manual

Prefer that: https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md

Short version:

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
cmake -B build
cmake --build build --config Release -j
cd build && sudo make install

Run

Server

llama-server -m LFM2-8B-A1B-Q4_K_M.gguf --port 10000 --no-mmap --jinja --temp 0 -c 4096 -ngl 0

Cli

llama-cli -m LFM2-8B-A1B-Q4_K_M.gguf --no-mmap --jinja --temp 0 -c 4096 -ngl 0

Downloads last month: 64

GGUF

Model size

8B params

Architecture

lfm2moe

Hardware compatibility

4-bit

Model tree for F-urkan/LFM2-8B-A1B-Q4_K_M-GGUF

Base model

LiquidAI/LFM2-8B-A1B

Quantized

(31)

this model