iiinova — where your digital self keeps evolving

Google Gemma {bot} @googlegemma.xmirror.bot · 15/10/2026

Welcome to the new Gemma documentation! We've built a brand new home for developers to explore, experiment, and build.

Google Gemma {bot} @googlegemma.xmirror.bot · 13/10/2026

What if Spotlight actually understood the meaning inside your files? DigUp is an open-source macOS menu bar app powered by EmbeddingGemma 2 that brings 100% local, multimodal semantic search to your Mac. Instead of searching for file names, you can use natural language to:

131 0

Google Gemma {bot} @googlegemma.xmirror.bot · 12/10/2026

How good are your sketching skills? Let an embedding model be the judge. Pick a target object, start sketching, and watch EmbeddingGemma 2 guess what you're making in real-time. Refine your drawing until you hit 90% similarity to beat the distractors and clear the level! 🎨

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 09/10/2026

Google AI Pro plans now package premium Colab benefits, landing you A100s with 80GB VRAM (Ultra subs even unlock H100s 🔥). Here’s what that 80GB headroom unlocks directly in your browser:

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 08/10/2026

Ready to start building with EmbeddingGemma 2? Our Developer Guide walks you through embedding multimodal content across text, code, images, video, and audio using the sentence-transformers library and more! The workflow:

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 07/10/2026

Finding the exact DNA that makes crops climate-resilient used to take years of physical breeding.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 06/10/2026

EmbeddingGemma 2 provides best-in-size-class performance for benchmarks like MTEB (Code) and MIEB (Lite). It’s well-suited for local codebase indexing, semantic code search, and coding agent retrieval, delivering a significant 9.92-point improvement on code performance over EmbeddingGemma.

130 0

Google Gemma {bot} @googlegemma.xmirror.bot · 06/10/2026

Introducing EmbeddingGemma 2! 🚀 Our lightweight, multimodal embedding model maps text, code, images, video, and audio into a single, unified embedding space. Optimized for on-device use cases, it features:

1113 0

Google Gemma {bot} @googlegemma.xmirror.bot · 01/10/2026

What if every student had the superpower of a personal tutor?

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 28/09/2026

Today’s best coding agents rely on massive API models running in the cloud. What if every developer could rely on an autonomous agent equally capable offline, on consumer hardware? We’re challenging you to close the gap. The Gemma 4 Developer Agent Competition with @Kaggle is live!

121 0

Google Gemma {bot} @googlegemma.xmirror.bot · 24/09/2026

Announcing the Google Gemma Hardware Hackathon at the legendary AGI House! Join us for the builder finale to Open Source AI Week. We’re hosting an intensive day dedicated to the future of physical AI. Apply now to get hands-on with the latest mobile, embedded and robotics hardware x Gemma models.

112 0

Google Gemma {bot} @googlegemma.xmirror.bot · 23/09/2026

Build agentic workflows completely offline. The Antigravity SDK now supports local execution with Gemma 4 and LiteRT. Run agents entirely on your local machine with: 💵 Zero token costs 🔒 Total data privacy 🔌 Offline reliability

120 0

Google Gemma {bot} @googlegemma.xmirror.bot · 23/09/2026

Deploying DiffusionGemma-Jev (djev) just got a lot easier. You can now spin up a Jev API-compatible endpoint on Google Cloud Run using a single command. Performance is solid: ~35-60 ms for single step latency and batch@32 is ~100-123 requests/sec.

1442 0

Google Gemma {bot} @googlegemma.xmirror.bot · 18/09/2026

"DiffusionGemma as Jev" showcases the power of non-autoregressive architectures. While Jev demonstrates the value of rapid decision models, running DiffusionGemma in this paradigm leverages canvas diffusion to evaluate structured choices in a single parallel pass:

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 17/09/2026

We prototyped a tactile desk robot using LEGO, a Raspberry Pi, and a hybrid LLM setup: ✨ Gemma 4 runs locally for instant, private zero-cost chat ✨ Auto-escalates to Gemini Flash for complex reasoning & code

110 0

Google Gemma {bot} @googlegemma.xmirror.bot · 17/09/2026

We prototyped, a tactile desk robot using LEGO, a Raspberry Pi, and a hybrid LLM setup: ✨ Gemma 4 runs locally for instant, private zero-cost chat ✨ Auto-escalates to Gemini Flash for complex reasoning & code

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 16/09/2026

Looking for a better local model that runs on a MacBook Air? Our latest update brings full Gemma 4 12B support to Google AI Edge Gallery app on Mac. ✨ Multimodal: Vision & Audio inputs 🎛️ Configurable vision token budgets ⚡️ MTP for blazing-fast inference 💻 Optimized to run on 16GB Macs!

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 14/09/2026

Standup Pulse: an open-source project running async Slack standups using Gemma 4 26B-A4B (GGUF via llama.cpp) on an Apple M5 Max.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 11/09/2026

Running AI in space requires strict power and bandwidth management.

101 0

Google Gemma {bot} @googlegemma.xmirror.bot · 10/09/2026

Sign language AI should not depend on Wi-Fi or expect Deaf folks to do all the adapting. Meet KawanIsyarat, a local-first mobile tool bridging BISINDO and spoken Indonesian offline using Gemma 4.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 09/09/2026

You don't need to be a command-line expert to run local AI.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 04/09/2026

Deploying AI at the edge makes local public service tools practical and accessible.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 03/09/2026

Gemma is only as powerful as the community building with it. We launched awesome-gemma to highlight amazing community-made tools, research, and applications in the ecosystem. What have you built? Drop a link below or submit a PR to get featured: github.com/google-gemma/awesome-gem…

000 0

Google Gemma {bot} @googlegemma.xmirror.bot · 01/09/2026

Running Gemma 4 26B A4B on a Mac just got 2x faster! The developer community has been grinding on the mlx.fast leaderboard, pushing Apple Silicon to its limits.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 31/08/2026

The latest technology should be accessible to the elderly, empowering them to navigate a changing world on the devices they already own. (1/3)

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 28/08/2026

Gemma 4 E2B running fully locally on an 8GB NVIDIA Jetson Orin Nano. Using native image/audio input and function calling, this edge setup is capable of vision, voice interaction, and camera control, all within an 8GB memory footprint!

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 25/08/2026

Fast and local voice typing with Gemma 4. Phonon demonstrates the utility of lightweight, on-device models for privacy-preserving workflows. This open-source voice typing tool runs Gemma 4 (E2B 4-bit) locally via MLX to process audio and screen context without cloud routing.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 24/08/2026

The wait is over. 🏆 We challenged you to use Gemma 4 to tackle real-world problems for the Gemma 4 Good Hackathon. Your submissions set a new standard for technical excellence and real-world impact. Meet the innovators who took home the top prizes.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 21/08/2026

You don't always need a frontier model. A recent benchmark found that Gemma 4 31B matches Sonnet 5 on answer quality at ~40x lower cost. With high cost-efficiency and low latency, Gemma unlocks high-volume use cases that are uneconomical with larger models.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 20/08/2026

Tonight we’re gathering in SF to celebrate 1 BILLION Gemma downloads! While we can only fit a few of you in the room, we’ll be raising a glass to the millions of developers worldwide who are driving the Gemmaverse forward. 🥂 (1/2)

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 17/08/2026

At 100 mph, there is no room for lag! Google Developer Experts built a real-time AI Race Coach at Sonoma Raceway. By running Gemma 4 locally on the Pixel 10, they delivered split-second, zero-latency audio coaching directly to the driver while out on track.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 14/08/2026

Bringing open models into the physical world. Check out this vibrant local assistant build from the Gemma 4 Good Hackathon. YANVI runs Gemma 4 locally on edge hardware, featuring a physical presence, an expression engine, and full desktop autonomy.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 13/08/2026

Ever wonder what makes Gemma 4 12B so unique? In this 2 minute overview series, learn what an encoder-free model is and how Gemma 4 12B processes image and audio inputs differently from the rest of the Gemma family!

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 12/08/2026

Can a $175 board power an offline robot voice assistant? 🤖 It’s cool to see Gemma 4 E2B powering the Reachy Mini robot entirely locally on a Raspberry Pi 5. Inference powered by LiteRT, it handles low latency voice, vision (YOLO) and robot movement completely offline. (1/2)

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 11/08/2026

🎉 1 BILLION DOWNLOADS 🎉 To celebrate this exciting milestone, we’re hosting an exclusive evening in SF on Aug 20 dedicated to YOU, the open-source builders, researchers, and contributors driving the Gemmaverse forward. (1/2)

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 10/08/2026

The complete DiffusionGemma technical report is officially live! We're sharing our full process and insights to help the community explore the incredible potential of text diffusion. We’re excited to see how this approach drives new research and applications.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 07/08/2026

Check out this interesting demo from the latest Gemma 4 hackathon. This live meeting copilot runs at 1,000+ tok/s, turning spoken conversations into working prototypes before the meeting even ends.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 06/08/2026

Meet the Gemma Translator! A fully offline device powered by Gemma 4 E2B built with @Antigravity. Running entirely on a Raspberry Pi 5 with a connected microphone and speaker, this highly portable prototype is housed inside a custom, 3D-printed case.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 05/08/2026

Wonder what the “E” stands for in E2B and E4B models? Look no further! Learn more about these “effective” parameters, Per-Layer Embeddings (PLE), and how they boost a model's power without increasing the actual parameters used during computation in this 2-minute overview.

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 04/08/2026

Gemma 4 running on an iPhone with just ~500 MB of RAM! (1/2)

100 0

Google Gemma {bot} @googlegemma.xmirror.bot · 31/07/2026

Ambient, real-world context is the future of AI! 🕶️ Check out this Gemma 4 hackathon demo: it captures input via smart glasses, processes context through a custom engine, and runs lightning-fast inference on high-performance hardware. See it in action!

100 0