Instructions to use miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use miifanboy/LFM2.5-2.6B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miifanboy/LFM2.5-2.6B-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": "miifanboy/LFM2.5-2.6B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M

Ollama
How to use miifanboy/LFM2.5-2.6B-GGUF with Ollama:
```
ollama run hf.co/miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
```

Unsloth Studio

How to use miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for miifanboy/LFM2.5-2.6B-GGUF to start chatting

How to use miifanboy/LFM2.5-2.6B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf miifanboy/LFM2.5-2.6B-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": "miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use miifanboy/LFM2.5-2.6B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf miifanboy/LFM2.5-2.6B-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 "miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF with Docker Model Runner:
```
docker model run hf.co/miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M
```

Lemonade

How to use miifanboy/LFM2.5-2.6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-2.6B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-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 miifanboy/LFM2.5-2.6B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

LFM2.5‑2.6B GGUF Quantizations

Overview

This repository contains the GGUF‑formatted quantized versions of the LiquidAI LFM2.5‑2.6B model. Each variant is named according to the LFM2.5-2.6B-<quant>.gguf scheme and is optimized for different trade‑offs between size and inference speed.

IMPORTANT FIX: It was not possible to disable thinking in LiquidAI/LFM2.5-2.6B-GGUF, these quants don't have that issue.

All quantizations were generated using the imatrix quantization pipeline. Note: the token_embd.weight layer was not quantized in any of these files.

imatrix calibration file is from bartowski

Written by LFM2.5-2.6B-Q8_0: This model card is written by the Q8_0 quant.

Quantization Table

Quant	File Name	Size (GB)
F16	`LFM2.5-2.6B-F16.gguf`	5.27
Q8_0	`LFM2.5-2.6B-Q8_0.gguf`	2.80
Q6_K	`LFM2.5-2.6B-Q6_K.gguf`	2.16
Q5_K_M	`LFM2.5-2.6B-Q5_K_M.gguf`	1.89
Q4_K_M	`LFM2.5-2.6B-Q4_K_M.gguf`	1.63
Q4_K_S	`LFM2.5-2.6B-Q4_K_S.gguf`	1.56
IQ4_NL	`LFM2.5-2.6B-IQ4_NL.gguf`	1.55
IQ4_XS	`LFM2.5-2.6B-IQ4_XS.gguf`	1.48
Q3_K_S	`LFM2.5-2.6B-Q3_K_S.gguf`	1.24
IQ3_XS	`LFM2.5-2.6B-IQ3_XS.gguf`	1.19
Q2_K	`LFM2.5-2.6B-Q2_K.gguf`	1.06

Notes

Imatrix Pipeline: All quantizations were created with the imatrix quantization tool. This method provides high‑quality compression while preserving model accuracy.
Token Embeddings: The token_embd.weight layer remains in full FP16 (or the original precision) and was not quantized. This ensures that embedding look‑ups remain accurate during inference.
KL Divergence Test: A KL‑divergence evaluation will be added to this repository shortly. Stay tuned for the updated benchmark results.

Usage

To load any of the quantized models, simply use the standard GGUF loader (e.g., llama.cpp or auto-gptq):

# Example with llama.cpp
./llama-server -m "./LFM2.5-2.6B-Q4_K_M.gguf" -c 128000

Replace the model file with any of the entries from the table above.

License

All models and quantizations are released under the LiquidAI LFM2.5‑2.6B license (see the model card for details).

For further questions or feedback, feel free to open an issue.

Downloads last month: 785

GGUF

Model size

3B params

Architecture

lfm2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for miifanboy/LFM2.5-2.6B-GGUF

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Quantized

(56)

this model