Instructions to use librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE",
	filename="SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M

Use Docker

docker model run hf.co/librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M

LM Studio
Jan

vLLM

How to use librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M

Ollama
How to use librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE with Ollama:
```
ollama run hf.co/librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
```

Unsloth Studio new

How to use librepowerai/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct-Q4_K_M-BE to start chatting

Docker Model Runner
How to use librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE with Docker Model Runner:
```
docker model run hf.co/librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M
```

Lemonade

How to use librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-1.7B-Instruct-Q4_K_M-BE-Q4_K_M

List all available models

lemonade list

SmolLM2-1.7B-Instruct Q4_K_M — Big-Endian

Big-endian GGUF of HuggingFaceTB/SmolLM2-1.7B-Instruct for IBM AIX and other big-endian POWER systems.

Why Big-Endian?

GGUF files store all data in little-endian. On big-endian systems (AIX, z/OS), llama.cpp detects the mismatch and fails. This pre-converted model works directly.

Model Details

Field	Value
Parameters	1.7B
Architecture	LLaMA-style transformer (SmolLM)
Quantization	Q4_K_M
Context length	8,192 tokens
File	`SmolLM2-1.7B-Instruct-Q4_K_M-be.gguf` (1.0 GB)
Endianness	Big-endian
Source	HuggingFaceTB/SmolLM2-1.7B-Instruct

Note: Requires proper chat template for best results.

Performance on IBM POWER9 (AIX 7.3)

Tested at 16 threads, SMT-2:

Generation: 17.94 tok/s
Prompt processing: 14.31 tok/s

Quick Start (AIX)

git clone https://gitlab.com/librepower/llama-aix.git
cd llama-aix
./scripts/fetch_upstream.sh && ./scripts/build_aix_73.sh
wget https://huggingface.co/librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE/resolve/main/SmolLM2-1.7B-Instruct-Q4_K_M-be.gguf
./build/bin/llama-simple -m SmolLM2-1.7B-Instruct-Q4_K_M-be.gguf -n 256 -t 16 "Your prompt"

LibrePower — Unlocking IBM Power Systems through open source. https://librepower.org | hello@librepower.org

Downloads last month: 12

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for librepowerai/SmolLM2-1.7B-Instruct-Q4_K_M-BE

Base model

HuggingFaceTB/SmolLM2-1.7B

Quantized

HuggingFaceTB/SmolLM2-1.7B-Instruct

Quantized

(89)

this model