Gemma 4 has been released — and now AI agents can be run directly on a laptop
Product Lead Oliver announced the launch of Gemma 4 — a family of open models based on Gemini 3 technology. Since the first Gemma, developers have achieved over 400 million downloads and more than 100,000 variants, creating an ecosystem around the models.
The Tech AI
Get the key points in seconds - a short summary from The Tech AI.
Gemma 4 — a lineup of models (2B, 4B, 26B MoE, 31B Dense) with an Apache 2.0 license for local deployment on PCs and mobile devices. It supports context up to 250,000 tokens, audio/video processing, and over 140 languages. Testing of the 2B model by Oliver confirmed its effectiveness in multilingual agentic tasks. It ensures security according to Google DeepMind standards and compatibility with familiar tools.
Key Features of Gemma 4
The models are designed to run on user-owned hardware—phones, laptops, and desktop PCs. For the first time, release under the Apache 2.0 license allows free use, modification, and distribution.
Gemma 4 is oriented toward the era of agents:
— handles complex logic
— multi-step planning
— workflows.
The large model supports a context window of up to 250,000 tokens for analyzing codebases and multi-turn scenarios. Built-in tool support enables agents to plan and act autonomously.
Gemma 4 Model Lineup
The 26B Mixture of Experts and 31B Dense models deliver cutting-edge intelligence on PCs. Run local reasoning and coding pipelines without sending data to the cloud.
— 26B MoE with 3.8 billion active parameters runs extremely fast
— 31B Dense is optimized for text generation quality.
The 2B and 4B models are built for mobile devices and IoT with maximum memory efficiency. Support for real-time audio and video, native operation in over 140 languages.
Testing the 2B Model
Oliver tested the efficient 2B model on a multilingual and agentic task. This was a real-world test of Gemma 4’s capabilities in everyday scenarios—a combination of understanding a French query, searching for information, and responding in English. “Gemma, can you find a French restaurant in San Francisco? Answer me in English.”
The model handled the task, executing a multi-step request without delays. It didn’t just translate; it applied agentic logic: found relevant data and provided an accurate response.
Security and Integration
Gemma 4 undergoes the same rigorous security protocols as Google DeepMind’s proprietary models.
This provides enterprises and developers with a reliable foundation for building applications and solutions. Gemma 4 is fully compatible with tools you already know. Model weights are available for download right now—start experimenting today.
The Tech on Telegram Follow The Tech on Telegram
Keep up with the latest technology and startup news.