Instructions to use zanish-labs/translategemma-4b-it-Q2_K-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 zanish-labs/translategemma-4b-it-Q2_K-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 zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

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 zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

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 zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

Use Docker

docker model run hf.co/zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

LM Studio
Jan
Ollama
How to use zanish-labs/translategemma-4b-it-Q2_K-gguf with Ollama:
```
ollama run hf.co/zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
```

Unsloth Studio

How to use zanish-labs/translategemma-4b-it-Q2_K-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 zanish-labs/translategemma-4b-it-Q2_K-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 zanish-labs/translategemma-4b-it-Q2_K-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zanish-labs/translategemma-4b-it-Q2_K-gguf to start chatting

Docker Model Runner
How to use zanish-labs/translategemma-4b-it-Q2_K-gguf with Docker Model Runner:
```
docker model run hf.co/zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K
```

Lemonade

How to use zanish-labs/translategemma-4b-it-Q2_K-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zanish-labs/translategemma-4b-it-Q2_K-gguf:Q2_K

Run and chat with the model

lemonade run user.translategemma-4b-it-Q2_K-gguf-Q2_K

List all available models

lemonade list

Atomic Chat

translategemma-4b-it-Q2_K-GGUF

GGUF-quantized derivative of Google's TranslateGemma 4B for on-device translation.

Base Model

Model: TranslateGemma 4B Instruct
Provider: Google
Source: https://huggingface.co/google/translategemma-4b-it
License: Gemma License (see LICENSE file)

Conversion Details

Source GGUF: mradermacher/translategemma-4b-it-GGUF
Quantization: Q2_K
GGUF Size: ~1.7 GB
Prepared by: Zanish Labs / Voco

Runtime

Compatible with llama.cpp (CPU/NEON)
Tested on Voco iOS app (STQ1_0 backend, PR #22836)

Attribution

This is a quantized derivative. The original model was created by Google. See LICENSE for full license text.

Model tree for zanish-labs/translategemma-4b-it-Q2_K-gguf

Base model

google/translategemma-4b-it

Quantized

(39)

this model