Gemma 4: Google's free AI model built to run locally
Google DeepMind has published Gemma 4 on Hugging Face, and the release is built around local deployment. The lineup includes four multimodal models, from E2B and E4B for edge devices to 26B A4B and 31B for workstations. The models ship under Apache 2.0 with up to 256K context and native image support. The smaller versions also handle audio.
AI-processed from Hugging Face Blog; edited by Hamidun News
Google DeepMind has released Gemma 4, a free multimodal model family on Hugging Face built for local deployment. It handles text and video on workstations and servers.
Is Gemma 4 free?
Yes. Gemma 4 is released under the Apache 2.0 license and is available for free on Hugging Face.
Which Gemma 4 versions can run on your own computer?
There are four versions: the compact E2B and E4B for edge devices, plus A4B (26B parameters) and a 31B version for workstations and servers. The smaller versions have a 128K context window; the larger ones support 256K.
Can Gemma 4 run locally?
Yes, and that is the main selling point of Gemma 4. The lineup includes four versions: E2B and E4B for edge scenarios, and 26B A4B and 31B for workloads on workstations and server hardware.
Which Gemma 4 versions are available?
Google released four versions: E2B and E4B for edge scenarios with a 128K context window, and A4B (26B) and 31B for heavier workloads on workstations with a 256K window.
Can Gemma 4 be used for free?
Yes. Gemma 4 is released under the Apache 2.0 license and is available on Hugging Face for local use without restrictions.
- Nov 2, 2026Bun creator uses Claude Code to port 750K lines from Zig to Rust in 11 days
- Nov 2, 2026The Verge reviewer builds a $50 Meta Muse Charm alternative with Claude Code
- Nov 1, 202616 models tested on 7 search tools: Exa averaged 10.5 out of 14, SearXNG about 3
- Nov 1, 2026Google's StreamVibe video agent beats other models by 10.7% on response timing and quality
Key Questions Answered
Is Gemma 4 free?
Yes. Gemma 4 is released under the Apache 2.0 license and is available for free on Hugging Face.
Which Gemma 4 versions can run on your own computer?
There are four versions: the compact E2B and E4B for edge devices, plus A4B (26B parameters) and a 31B version for workstations and servers. The smaller versions have a 128K context window; the larger ones support 256K.
Can Gemma 4 run locally?
Yes, and that is the main selling point of Gemma 4. The lineup includes four versions: E2B and E4B for edge scenarios, and 26B A4B and 31B for workloads on workstations and server hardware.
Which Gemma 4 versions are available?
Google released four versions: E2B and E4B for edge scenarios with a 128K context window, and A4B (26B) and 31B for heavier workloads on workstations with a 256K window.
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.