Instructions to use mixer3d/translategemma-4b-it-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mixer3d/translategemma-4b-it-gguf 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 mixer3d/translategemma-4b-it-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf mixer3d/translategemma-4b-it-gguf:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mixer3d/translategemma-4b-it-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf mixer3d/translategemma-4b-it-gguf:Q5_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 mixer3d/translategemma-4b-it-gguf:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf mixer3d/translategemma-4b-it-gguf:Q5_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 mixer3d/translategemma-4b-it-gguf:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mixer3d/translategemma-4b-it-gguf:Q5_K_M

Use Docker

docker model run hf.co/mixer3d/translategemma-4b-it-gguf:Q5_K_M

LM Studio
Jan

vLLM

How to use mixer3d/translategemma-4b-it-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mixer3d/translategemma-4b-it-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mixer3d/translategemma-4b-it-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/mixer3d/translategemma-4b-it-gguf:Q5_K_M

Ollama
How to use mixer3d/translategemma-4b-it-gguf with Ollama:
```
ollama run hf.co/mixer3d/translategemma-4b-it-gguf:Q5_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mixer3d/translategemma-4b-it-gguf with Docker Model Runner:
```
docker model run hf.co/mixer3d/translategemma-4b-it-gguf:Q5_K_M
```

Lemonade

How to use mixer3d/translategemma-4b-it-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mixer3d/translategemma-4b-it-gguf:Q5_K_M

Run and chat with the model

lemonade run user.translategemma-4b-it-gguf-Q5_K_M

List all available models

lemonade list

Atomic Chat

translategemma-4b-it-q5_k_m.gguf

This repo contains GGUF weights for google/translategemma-4b-it.

Quantization Details

Method: llama-quantize
Llama.cpp Version: 7770 (fe44d3557)
Original Model Precision: BF16

Files Provided

File	Quant Method	Size	Description
`translategemma-4b-it-q5_k_m.gguf`	Q5_K_M	3.2 GB	High quality, recommended for most uses.

Usage

You can use these models with llama.cpp

./llama-server -m translategemma-4b-it-q5_k_m.gguf -no-mmap -ngl 99 --port 8080 -c 8192 -fa 1 --jinja

Downloads last month: 7

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

5-bit

Model tree for mixer3d/translategemma-4b-it-gguf

Base model

google/translategemma-4b-it

Quantized

(44)

this model