Google Gemma
Google DeepMind's open weight LLM family built from the same research as Gemini, now in its fourth generation with sizes from E2B to 31B parameters.
What it is
Gemma is a family of open weight large language models by Google DeepMind. The name comes from the Latin word for gemstone. Built from the same research and technology that powers the Gemini models, Gemma is independently trained for lightweight, accessible deployment across a wide range of hardware. With over 400 million downloads and more than 100,000 community variants on Hugging Face, Gemma has become one of the most widely adopted open model families in the world. The current generation is Gemma 4 (released April 2026), built from Gemini 3 research, purpose built for advanced reasoning and agentic workflows. Gemma 4 is available in four sizes: E2B, E4B, 26B (Mixture of Experts with 4B active parameters), and 31B (Dense). The larger models offer a 256K token context window, while edge models support 128K. All models process text, images, and video, and the E2B and E4B models also support native audio input. The ecosystem includes specialized variants such as MedGemma for medical applications, CodeGemma for code tasks, PaliGemma for vision and language, and ShieldGemma for content safety. Gemma 4 is licensed under the Apache 2.0 license, a major change from the previous Gemma Terms of Use, providing full open source flexibility. The Gemma 4 31B model achieved an Arena AI rating of 1452, ranking as the #3 open model in the world on the Arena AI text leaderboard.
Who it is for
Developers wanting to run AI models locally on their own hardware without API dependencies or usage fees
Researchers needing an open model they can fine tune, modify, and experiment with for academic and applied work
Companies wanting to deploy AI on premises for complete data privacy and regulatory compliance
Mobile developers needing on device models for apps that work offline or with minimal latency (Gemma 4 E2B/E4B)
Specialized applications in healthcare (MedGemma), content safety (ShieldGemma), code generation (CodeGemma), and translation (TranslateGemma)
Pros and cons
Pros
- +Completely free to download and use, with no API fees or usage limits when self hosted
- +Runs on consumer hardware: quantized Gemma 4 models run natively on consumer GPUs, and E2B/E4B run on smartphones and edge devices
- +Up to 256K token context window on Gemma 4 larger models (128K on edge models), competitive with much larger proprietary models
- +Multimodal input (text, image, video) across all Gemma 4 sizes, plus native audio on E2B/E4B edge models
- +Massive community with 400M+ downloads and 100,000+ fine tuned variants on Hugging Face
- +Specialized variants for medical, safety, code, vision, and translation tasks, ready to use out of the box
- +Quantization aware trained checkpoints maintain high quality even at INT4 precision, maximizing hardware efficiency
- +Built from the same research as Gemini, delivering frontier quality relative to model size
Cons
- −Gemma 4 is Apache 2.0, but older Gemma 3 and earlier models remain under the more restrictive Gemma Terms of Use, so check which generation you are using
- −Smaller than proprietary Gemini models (31B max vs Gemini's much larger architectures), so raw capability has a ceiling
- −As an open weight model you run locally, there is no live data access, so responses are limited to the model's training data cutoff
- −Audio input is only available on the E2B and E4B edge models; the 26B and 31B models do not support native audio
- −Requires technical setup to run locally: downloading models, configuring inference frameworks, and managing hardware resources
- −The E2B edge model is limited in reasoning capability compared to the larger sizes and is best suited for simple on device tasks or fine tuned applications
Pricing
- All model sizes (E2B, E4B, 26B, 31B) free to download
- Full model weights on Hugging Face, Kaggle, and Ollama
- Run locally via Ollama, llama.cpp, vLLM, LM Studio, or any compatible framework
Prices change; check the official pricing →