Instructions to use h4shy/gemma-3-1b-it-fast-GUFF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h4shy/gemma-3-1b-it-fast-GUFF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="h4shy/gemma-3-1b-it-fast-GUFF",
	filename="gemma3-1b-Q5_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use h4shy/gemma-3-1b-it-fast-GUFF 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 h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
# Run inference directly in the terminal:
llama cli -hf h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
# Run inference directly in the terminal:
llama cli -hf h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

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 h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
# Run inference directly in the terminal:
./llama-cli -hf h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

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 h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

Use Docker

docker model run hf.co/h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

LM Studio
Jan

vLLM

How to use h4shy/gemma-3-1b-it-fast-GUFF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h4shy/gemma-3-1b-it-fast-GUFF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h4shy/gemma-3-1b-it-fast-GUFF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

Ollama
How to use h4shy/gemma-3-1b-it-fast-GUFF with Ollama:
```
ollama run hf.co/h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
```

Unsloth Studio

How to use h4shy/gemma-3-1b-it-fast-GUFF 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 h4shy/gemma-3-1b-it-fast-GUFF 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 h4shy/gemma-3-1b-it-fast-GUFF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for h4shy/gemma-3-1b-it-fast-GUFF to start chatting

Atomic Chat new
Docker Model Runner
How to use h4shy/gemma-3-1b-it-fast-GUFF with Docker Model Runner:
```
docker model run hf.co/h4shy/gemma-3-1b-it-fast-GUFF:Q5_0
```

Lemonade

How to use h4shy/gemma-3-1b-it-fast-GUFF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull h4shy/gemma-3-1b-it-fast-GUFF:Q5_0

Run and chat with the model

lemonade run user.gemma-3-1b-it-fast-GUFF-Q5_0

List all available models

lemonade list

I quantized this model for my CPU-only setup: i5-3450 (AVX1). I use it for some behind-the-scenes production tasks and it has been reliable.

Go with the Q5_0 if you want to save your little ram for like a minecraft server or something

Original model: gemma-3-1b-it
Software used for quantization: llama.cpp

Downloads last month: 108

GGUF

Model size

1.0B params

Architecture

gemma3

Hardware compatibility

5-bit

8-bit

Model tree for h4shy/gemma-3-1b-it-fast-GUFF

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Quantized

(447)

this model