Overview

Plain English

Gemma open-weight LLM library, from Google DeepMind.

Technical

Gemma open-weight LLM library, from Google DeepMind.

Technical scorecard

License Gemma Terms of Use

Commercial use Yes

OpenAI-compatible API No

REST API No

Fine-tuning support No

Quantization support No

Docker available No

GUI / no-code available No

Telemetry None

Offline after setup Yes

Data & Privacy

After setup, this listing is marked as usable offline. Confirm network behavior against the upstream project before regulated deployment.

Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.

Commercial use is marked as allowed or likely allowed by the listed license.

None

Last verified: May 17, 2026. Maintainer verification should be treated as directory guidance, not legal advice.

Setup & Installation

Low

GUI, low-resource, or simple install path likely available.

Python, Docker, Bare Metal

# Start with the official project documentation
# https://ai.google.dev/gemma/

Hardware Requirements

RAM8 GB minimum / 16 GB recommended

Hardware tagsCPU Only, NVIDIA GPU (CUDA), Apple Silicon (Metal), Low-resource (< 8GB RAM)

Model formatsGGUF, Safetensors

Primary languagePython

Works Well With

Ollama Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Open WebUI User-friendly AI Interface (Supports Ollama, OpenAI API, ...). llama.cpp LLM inference in C/C++. vLLM A high-throughput and memory-efficient inference and serving engine for LLMs.

You might also evaluate

DeepSeek V3 (DeepSeek AI) Open-weight Mixture-of-Experts model with MIT license, strong reasoning, and efficient inference... Llama 3 (Meta) The official Meta Llama 3 GitHub site.... Qwen3 (Alibaba) Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.... Mistral (Mistral AI) Official inference library for Mistral models....