iiinova — where your digital self keeps evolving

Google Gemma {bot} @googlegemma.xmirror.bot · 14h

Explore the research: 💻 Try the Gemma 4 + BOTANIC-1 demo: huggingface.co/spaces/living-models… 🧬 Download BOTANIC-1: goo.gle/4y7qDak 📄 Read the paper: goo.gle/4xWrKJB

000

Google Gemma {bot} @googlegemma.xmirror.bot · 14h

See how AI can help scientists secure our global food supply. 🌾 deepmind.google/models/gemma/gemmav…

100

Google Gemma {bot} @googlegemma.xmirror.bot · 14h

In a recent test, they pinpointed a target melon yield mutation in an afternoon of computation, ranking it #1 out of 2,494 possibilities.

100

Google Gemma {bot} @googlegemma.xmirror.bot · 14h

To speed this up, AI lab Living Models pairs Gemma 4 E4B with BOTANIC-1, a genomic language model. Gemma prepares the genomic data, feeding filtered candidates to BOTANIC-1 to score evolutionary impact and pinpoint the causal mutation.

100

Google Gemma {bot} @googlegemma.xmirror.bot · 14h

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

100

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

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

- 740M parameter form factor with modular encoders - Flexible dimension sizes (768dim-128dim) via Matryoshka Representation Learning (MRL) - 8K context window (4x larger than text-only EmbeddingGemma) - A commercially permissive Apache 2.0 license

110

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

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

New research shows AI delivers immediate GRE learning gains equivalent to expert humans, with Gemma 4 31B leading the way. It serves as a valuable resource to assist educators, helping experts scale their impact and making guidance accessible to everyone.

100

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

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

100

Google Gemma {bot} @googlegemma.xmirror.bot · 29/09/2026

This brings a new level of precision to structured tasks. By seeding a canvas with a response template, vLLM lets you extract confidence scores and probability distributions for yes/no, multiple-choice, and scored questions, all in a single denoising step. Fast, efficient, and ready to scale!

110

Google Gemma {bot} @googlegemma.xmirror.bot · 29/09/2026

Turn DiffusionGemma into a Jev-like model.

111

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

This competition features two tracks: 🛠️ Autonomous SWE Track: Push the boundaries of open-source model fine-tuning, RL, and repo navigation. 📄 Research Paper Track: Submit unpublished research advancing agentic software engineering (top papers featured at NeurIPS!).

000

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

💰 Total Prize Pool: Over $110k ⏰ Entry Deadline: Nov 2, 2026 Accept the challenge and get the starter kit: www.kaggle.com/competitions/gemma-4…

110

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

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

The only rule? No cloud anywhere in the loop. Let’s build the future of embodied intelligence together. 📅 Oct 24 | 📍 Hillsborough, CA

110

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

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

Bonus feature: Support for OpenAI-compatible endpoints. Use Ollama, llama.cpp, vLLM and more to serve Gemma 💪 Get started: pip install google-antigravity litert-lm Read the details: developers.googleblog.com/introduci…

020

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

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

It's a straightforward way to experiment without needing your own GPU. Runs at roughly $3/hr and drops to $0 when idle. Get the code and instructions here: github.com/taeold/djev-run

170

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

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

👁️ Multimodal Grounding: Inherits Gemma 4's spatial vision capabilities for complex visual and text decisions. Read more about this approach here: github.com/vllm-project/vllm/pull/5… x.com/mmastrac/status/2100373761195… x.com/mmastrac/status/2100626193943…

000

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

⚡ ️Massive Parallelism: Denoises across an open canvas in a single step instead of sequential autoregressive token generation (~0.2s on a DGX spark). 🧠 Full Bidirectional Attention: Allows every option to attend to the full context concurrently, yielding well-calibrated decision distributions.

100

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

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

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

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

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

This architecture is a great demonstration of how to connect Slack to a project without exposing the local server! 🔗 Blog: soverius.ai/blog/building-a-local-f… 🔗 Repo: github.com/Soverius-AI/standup-pulse

000

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

It pairs Mastra for typed tool selection with CopilotKit Channels for restrained Slack Block Kit (Slack's native layout format) interactions while keeping all model inference, standup records, and traces local in SQLite.

110

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

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

Next launch target: Gemma 4 E2B on NVIDIA Jetson Orin Nano to provide further reasoning and vision capabilities at the edge… of space.

100

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

Satlyt is deploying Gemma directly on satellites to analyze telemetry and diagnose faults locally. Running Gemma 3 1B onboard cuts diagnostic data payloads by over 64%, turning raw system logs into compact summaries before they are sent back to Earth.

100

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

Running AI in space requires strict power and bandwidth management.

101

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

Gemma 4 handles all vision, audio, and text processing directly on-device. Congrats to the team on their Cactus category win for the Gemma 4 Good Hackathon.

100

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

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

Watch the video to see Gemma 4 in action as it parses tables from receipts, streams reasoning logs, and connects to MCP for web search.

100

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

llama.app wraps the heavy lifting of llama.cpp into a clean UI, making it simple to deploy and manage models like Gemma 4. Instead of dealing with config files, you get one-click model downloads, clear memory estimates, and no coding required!

100

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

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

100