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

Libraries

How to use medmekk/SmolLM2-1.7B-Instruct.GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="medmekk/SmolLM2-1.7B-Instruct.GGUF",
	filename="SmolLM2-1.7B-Instruct-IQ3_M_imat.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use medmekk/SmolLM2-1.7B-Instruct.GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf medmekk/SmolLM2-1.7B-Instruct.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 medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf medmekk/SmolLM2-1.7B-Instruct.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 medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M

Use Docker

docker model run hf.co/medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use medmekk/SmolLM2-1.7B-Instruct.GGUF with Ollama:
```
ollama run hf.co/medmekk/SmolLM2-1.7B-Instruct.GGUF:Q4_K_M
```

Unsloth Studio new

How to use medmekk/SmolLM2-1.7B-Instruct.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 medmekk/SmolLM2-1.7B-Instruct.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 medmekk/SmolLM2-1.7B-Instruct.GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for medmekk/SmolLM2-1.7B-Instruct.GGUF to start chatting

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

Lemonade

How to use medmekk/SmolLM2-1.7B-Instruct.GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

medmekk/SmolLM2-1.7B-Instruct.GGUF

GGUF quantized versions of HuggingFaceTB/SmolLM2-1.7B-Instruct

Available Formats:

Q2_K: SmolLM2-1.7B-Instruct-Q2_K.gguf
Q3_K_S: SmolLM2-1.7B-Instruct-Q3_K_S.gguf
Q3_K_M: SmolLM2-1.7B-Instruct-Q3_K_M.gguf
Q3_K_L: SmolLM2-1.7B-Instruct-Q3_K_L.gguf
Q4_0: SmolLM2-1.7B-Instruct-Q4_0.gguf
Q4_K_S: SmolLM2-1.7B-Instruct-Q4_K_S.gguf
Q4_K_M: SmolLM2-1.7B-Instruct-Q4_K_M.gguf
Q5_0: SmolLM2-1.7B-Instruct-Q5_0.gguf
Q5_K_S: SmolLM2-1.7B-Instruct-Q5_K_S.gguf
Q5_K_M: SmolLM2-1.7B-Instruct-Q5_K_M.gguf
Q6_K: SmolLM2-1.7B-Instruct-Q6_K.gguf
Q8_0: SmolLM2-1.7B-Instruct-Q8_0.gguf
IQ3_M_IMAT: SmolLM2-1.7B-Instruct-IQ3_M_imat.gguf
IQ3_XXS_IMAT: SmolLM2-1.7B-Instruct-IQ3_XXS_imat.gguf
Q4_K_M_IMAT: SmolLM2-1.7B-Instruct-Q4_K_M_imat.gguf
Q4_K_S_IMAT: SmolLM2-1.7B-Instruct-Q4_K_S_imat.gguf
IQ4_NL_IMAT: SmolLM2-1.7B-Instruct-IQ4_NL_imat.gguf
IQ4_XS_IMAT: SmolLM2-1.7B-Instruct-IQ4_XS_imat.gguf
Q5_K_M_IMAT: SmolLM2-1.7B-Instruct-Q5_K_M_imat.gguf
Q5_K_S_IMAT: SmolLM2-1.7B-Instruct-Q5_K_S_imat.gguf

Usage with llama.cpp:

# CLI:
llama-cli --hf-repo medmekk/SmolLM2-1.7B-Instruct.GGUF --hf-file MODEL_FILE -p "Your prompt"

# Server:
llama-server --hf-repo medmekk/SmolLM2-1.7B-Instruct.GGUF --hf-file MODEL_FILE -c 2048

Downloads last month: 273

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Collection including medmekk/SmolLM2-1.7B-Instruct.GGUF

GGUF

Collection

Your favorite models quantized in gguf formats • 7 items • Updated Feb 2, 2025