Gemma

What is Gemma?

Gemma is a family of generative artificial intelligence models of use for a variety of generation tasks, including question answering, summarization, and reasoning. Gemma models are provided with open weights and permit responsible commercial use, allowing users to tune and deploy them in projects and applications.

Gemma 4 model family spans three distinct architectures tailored for specific hardware requirements:

Small Sizes: 2B and 4B effective parameter models built for ultra-mobile, edge, and browser deployment (e.g., Pixel, Chrome).
Dense: A powerful 31B parameter dense model that bridges the gap between server-grade performance and local execution.
Mixture-of-Experts: A highly efficient 26B MoE model designed for high-throughput, advanced reasoning.

Capabilities

Reasoning: All models in the family are designed as highly capable reasoners, with configurable thinking modes.
Extended Multimodalities: Processes Text, Image with variable aspect ratio and resolution support (all models), Video, and Audio (featured natively on the E2B and E4B models).
Increased Context Window: Small models feature a 128K context window, while the medium models support 256K.
Enhanced Coding & Agentic Capabilities: Achieves notable improvements in coding benchmarks alongside built-in function-calling support, powering highly capable autonomous agents.
Native System Prompt Support: Gemma 4 introduces built-in support for the system role, enabling more structured and controllable conversations.

Gemma is run using Ollama or LM Studio.