Instructions to use Codingstark/gemma3-270m-leetcode-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Codingstark/gemma3-270m-leetcode-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Codingstark/gemma3-270m-leetcode-gguf",
	filename="Gemma-3-leetcode.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 Codingstark/gemma3-270m-leetcode-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Codingstark/gemma3-270m-leetcode-gguf
# Run inference directly in the terminal:
llama-cli -hf Codingstark/gemma3-270m-leetcode-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Codingstark/gemma3-270m-leetcode-gguf
# Run inference directly in the terminal:
llama-cli -hf Codingstark/gemma3-270m-leetcode-gguf

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 Codingstark/gemma3-270m-leetcode-gguf
# Run inference directly in the terminal:
./llama-cli -hf Codingstark/gemma3-270m-leetcode-gguf

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 Codingstark/gemma3-270m-leetcode-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Codingstark/gemma3-270m-leetcode-gguf

Use Docker

docker model run hf.co/Codingstark/gemma3-270m-leetcode-gguf

LM Studio
Jan
Ollama
How to use Codingstark/gemma3-270m-leetcode-gguf with Ollama:
```
ollama run hf.co/Codingstark/gemma3-270m-leetcode-gguf
```

Unsloth Studio new

How to use Codingstark/gemma3-270m-leetcode-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 Codingstark/gemma3-270m-leetcode-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 Codingstark/gemma3-270m-leetcode-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Codingstark/gemma3-270m-leetcode-gguf to start chatting

Docker Model Runner
How to use Codingstark/gemma3-270m-leetcode-gguf with Docker Model Runner:
```
docker model run hf.co/Codingstark/gemma3-270m-leetcode-gguf
```

Lemonade

How to use Codingstark/gemma3-270m-leetcode-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Codingstark/gemma3-270m-leetcode-gguf

Run and chat with the model

lemonade run user.gemma3-270m-leetcode-gguf-{{QUANT_TAG}}

List all available models

lemonade list

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

Check out the documentation for more information.

gemma3-270m-leetcode-gguf

Original model: Codingstark/gemma3-270m-leetcode Format: GGUF Quantization: bf16

This is a GGUF conversion of the Codingstark/gemma3-270m-leetcode model, optimized for use with applications like LM Studio, Ollama, and other GGUF-compatible inference engines.

Usage

Load this model in any GGUF-compatible application by referencing the .gguf file.

Model Details

Original Repository: Codingstark/gemma3-270m-leetcode
Converted Format: GGUF
Quantization Level: bf16
Compatible With: LM Studio, Ollama, llama.cpp, and other GGUF inference engines

Conversion Process

This model was converted using the llama.cpp conversion scripts with the following settings:

Input format: Hugging Face Transformers
Output format: GGUF
Quantization: bf16

License

Please refer to the original model's license terms.

Downloads last month: 38

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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