Instructions to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ronniross/LFM2.5-1.2B-Base-f16-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 ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf ronniross/LFM2.5-1.2B-Base-f16-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 ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf ronniross/LFM2.5-1.2B-Base-f16-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 ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

Use Docker

docker model run hf.co/ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

LM Studio
Jan
Ollama
How to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with Ollama:
```
ollama run hf.co/ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
```
Unsloth Desktop

How to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with Docker Model Runner:
```
docker model run hf.co/ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16
```

Lemonade

How to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Base-f16-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use ronniross/LFM2.5-1.2B-Base-f16-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 ronniross/LFM2.5-1.2B-Base-f16-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 ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ronniross/LFM2.5-1.2B-Base-f16-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16

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 "ronniross/LFM2.5-1.2B-Base-f16-GGUF:F16" \
  --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"

ko-fi github

LFM2.5-1.2B-f16-GGUF

1. Conversion tutorial (from .safetensors to .gguf)

1.1 Navigate to your base-model folder on your working directory and clone the base model

cd C:\models\base_models

git clone https://huggingface.co/Qwen/LFM2.5-1.2B

You must see config.json, model.safetensors, and tokenizer files in there.

1.3 Navigate to your working directory and clone the llama repository

cd C:\models\

git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp

the content of the conversion depency will be at C:\models\llama.cpp

1.4 Install the CORRECT dependencies for Hugging Face conversion

pip install -r requirements/requirements-convert_hf_to_gguf.txt

1.5 pre-compiled llama.cpp

Go to the official releases page: llama.cpp Releases

Look for the latest release and download the Windows .zip file (usually named something like llama-bXXXX-bin-win-vulcan-x64.zip or llama-...-bin-win-avx2-x64.zip).

You can also compile using C++ on Windows, which requires CMake and Visual Studio tools, but since I find easier to just download the pre-compiled .exe I did it like that

1.6 Move additional dependencies

Move the content unzipped folder and paste it directly into your C:\models\llama.cpp folder or where you set to download the item 1.3

1.7 Conversion run

Now, we run the Python script to translate the Hugging Face format into a raw 16-bit GGUF file. Make sure you are still inside the llama.cpp directory at your terminal.

python convert_hf_to_gguf.py "C:\models\base_models\LFM2.5-1.2B" --outtype f16 --outfile "C:\models\base_models\LFM2.5-1.2B\LFM2.5-1.2B-Base-f16.gguf"

Ronni Ross
2026

Downloads last month: 11

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

16-bit

Inference Providers NEW

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