Instructions to use Vana-Labs/llm-gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Vana-Labs/llm-gemma 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 Vana-Labs/llm-gemma:Q8_0
# Run inference directly in the terminal:
llama cli -hf Vana-Labs/llm-gemma:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Vana-Labs/llm-gemma:Q8_0
# Run inference directly in the terminal:
llama cli -hf Vana-Labs/llm-gemma:Q8_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 Vana-Labs/llm-gemma:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Vana-Labs/llm-gemma:Q8_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 Vana-Labs/llm-gemma:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Vana-Labs/llm-gemma:Q8_0

Use Docker

docker model run hf.co/Vana-Labs/llm-gemma:Q8_0

LM Studio
Jan

vLLM

How to use Vana-Labs/llm-gemma with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Vana-Labs/llm-gemma:Q8_0

Ollama
How to use Vana-Labs/llm-gemma with Ollama:
```
ollama run hf.co/Vana-Labs/llm-gemma:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use Vana-Labs/llm-gemma with Docker Model Runner:
```
docker model run hf.co/Vana-Labs/llm-gemma:Q8_0
```

Lemonade

How to use Vana-Labs/llm-gemma with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Vana-Labs/llm-gemma:Q8_0

Run and chat with the model

lemonade run user.llm-gemma-Q8_0

List all available models

lemonade list

Atomic Chat

llm-gemma

Gemma 3 summary models for Tetro, the local meeting transcriber by Vana Labs, in GGUF format. They run fully on your computer.

This repository is a pinned mirror, so Tetro's downloads don't depend on third-party hosts. The files are unchanged copies.

File	Tetro model ID	Source
`gemma-3-1b-it-Q8_0.gguf`	`gemma3:1b`	bartowski/google_gemma-3-1b-it-GGUF
`gemma-3-4b-it-Q4_K_M.gguf`	`gemma3:4b`	bartowski/google_gemma-3-4b-it-GGUF

Source commits: bartowski/google_gemma-3-1b-it-GGUF 116f76234503685a98f572982177b11d44ec8ff1, bartowski/google_gemma-3-4b-it-GGUF 71506238f970075ca85125cd749c28b1b0eee84e.

Gemma notice

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms. Use of these files is also subject to the Gemma Prohibited Use Policy at ai.google.dev/gemma/prohibited_use_policy.

Downloads last month: 8

GGUF

Model size

1.0B params

Architecture

gemma3

Hardware compatibility

4-bit

8-bit

Model tree for Vana-Labs/llm-gemma

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Quantized

(474)

this model