Instructions to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE",
	filename="LFM2.5-1.2B-Instruct-Q4_K_M-be.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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE: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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE: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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

Use Docker

docker model run hf.co/librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

LM Studio
Jan

vLLM

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

Ollama
How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with Ollama:
```
ollama run hf.co/librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
```

Unsloth Studio

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE 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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE 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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE to start chatting

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE: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": "librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE: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 librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with Docker Model Runner:
```
docker model run hf.co/librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M
```

Lemonade

How to use librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Instruct-Q4_K_M-BE-Q4_K_M

List all available models

lemonade list

LFM2.5-1.2B-Instruct Q4_K_M — Big-Endian

Big-endian GGUF conversion of LiquidAI/LFM2.5-1.2B-Instruct for IBM AIX and other big-endian POWER systems.

Why Big-Endian?

The GGUF format stores all weights and metadata in little-endian byte order. Loading a standard GGUF file on a big-endian system (AIX, z/OS, etc.) produces garbage — every number is byte-reversed. llama.cpp does not perform runtime byte swapping; it detects the mismatch and fails:

failed to load model: this GGUF file version is extremely large,
is there a mismatch between the host and model endianness?

This pre-converted model works directly on big-endian systems without any additional conversion step.

Model Details

Field	Value
Base model	LiquidAI/LFM2.5-1.2B-Instruct
Architecture	lfm2 hybrid (10 shortconv + 6 GQA attention layers)
Parameters	1.17B
Quantization	Q4_K_M
Context window	128,000 tokens
File size	695 MB
Endianness	Big-endian
Source GGUF	LiquidAI/LFM2.5-1.2B-Instruct-GGUF

Performance on IBM POWER9 (AIX 7.3)

Tested on IBM Power System S924 (POWER9 @ 2.75 GHz), SMT-2 mode:

Threads	Generation (tok/s)
1	3.15
4	10.52
8	18.28
16	26.9

Memory usage: ~744 MB (model + compute buffers at 16 threads).

Quick Start (AIX)

# Clone and build llama.cpp for AIX
git clone https://gitlab.com/librepower/llama-aix.git
cd llama-aix
./scripts/fetch_upstream.sh
./scripts/build_aix_73.sh

# Download this model
wget https://huggingface.co/librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE/resolve/main/LFM2.5-1.2B-Instruct-Q4_K_M-be.gguf

# Set optimal SMT mode
smtctl -t 2 -w now

# Run inference
export LIBPATH=$PWD/build/bin:$LIBPATH
./build/bin/llama-simple \
    -m LFM2.5-1.2B-Instruct-Q4_K_M-be.gguf \
    -n 256 -t 16 \
    "You are an AIX admin. Analyze this error log entry:"

How This Model Was Converted

# From the original little-endian GGUF
pip install gguf
echo "YES" | python3 -m gguf.scripts.gguf_convert_endian \
    LFM2.5-1.2B-Instruct-Q4_K_M.gguf big

The conversion swaps every tensor, metadata field, and quantization block from little-endian to big-endian. The process takes about 15 seconds on a modern laptop.

llama-aix — llama.cpp port for AIX
TinyLlama 1.1B Big-Endian — Another big-endian model
Blog: Running LFM2.5 on AIX
LibrePower AIX Repository

License

This model inherits the license from the base model: LiquidAI/LFM2.5-1.2B-Instruct.

LibrePower — Unlocking IBM Power Systems through open source.

https://librepower.org | hello@librepower.org

Downloads last month: 20

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

4-bit

Model tree for librepowerai/LFM2.5-1.2B-Instruct-Q4_K_M-BE

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Quantized

(49)

this model

librepowerai
/

LFM2.5-1.2B-Instruct-Q4_K_M-BE