Google Release Notes

Create images inspired by your life

Connect your Google apps to Gemini to let Nano Banana 2 turn your stories into stunning visuals.

Creativity

Create a space for your projects and chats in Gemini

Add your chats and sources to notebooks in Gemini and jump back into projects fast.

Productivity

Personal Intelligence is going global

Connect your Google apps to Gemini for help that’s unique to you.

Productivity

Create music with Lyria 3 Pro at no cost

Mix and customize your sound in entirely new ways with tracks up to three minutes long at no cost.

Creativity

Gemini, now on macOS

Open the Gemini app from any screen on macOS, share what you’re working on, and get instant help.

Models

Understand complex concepts visually

Turn your tough questions into custom interactive visuals directly in your chat with Gemini.

Creativity

Help that’s made for you

Gemini connects across your Google apps for highly personalized help, from vacation ideas to project plans. Manage your settings anytime.

Personal Intelligence

Let Gemini in Chrome automate your tasks with auto browse

From appointment booking to party planning, tell Gemini what you need and watch it handle the rest for you, all while keeping you in control.

On your device

Better social videos, sized just right

Veo 3.1 videos generated from your vertical photos will now automatically stay in the same aspect ratio.

Creativity

Create expressive videos from images with Veo 3.1

Turn reference photos into dynamic, expressive videos with richer dialogue and storytelling, even when using simple prompts.

Creativity

Test prep like a pro

Practice for the (SAT/JEE) in Gemini with full-length tests, get feedback on your performance, and learn tips to help you focus your studying.

Learning

Gemini in Chrome now has better shopping help

Research products and find complementary items with results based on your open tabs.

On your device

Gemini in Chrome, now on iOS

Get answers and page summaries using the context of your current tab with Gemini in Chrome on your iPhone.

On your device

We previously launched support for sending full HD video (1080p) in Meet on the web, and we’re now extending that capability to Google Meet room hardware based on ChromeOS.

Google Meet will use full HD when the additional bandwidth is needed for sharp video from the room, such as:

• On large screens: When others in the call are viewing the room on large monitors or TVs with a layout that makes 1080p necessary, such as full-screen views in Spotlight mode, 1:1 calls or dual-screen rooms.
• When someone pins your video: If a person in the meeting "pins" the room, Meet will send the highest available quality.
• When the meeting is being recorded: Recorded meetings use full HD from the room for the saved meeting video.

Full HD is available from devices that use a high-resolution camera and can handle the additional processing over a fast, stable internet connection. Meet will continue to automatically adjust video quality downwards if network constraints are detected to ensure a smooth meeting experience.

Getting started

• Admins: There is no admin control for this feature.
• End users: There is no end user setting for this feature; the upgrade happens seamlessly in the background when conditions are met.

Rollout pace

• Rapid Release and Scheduled Release domains: Available now

Availability

• Available to all Google Workspace customers with Google Meet hardware devices

Resources

• Google Meet Help: Learn how to view people in Google Meet
• Google Meet Help: Pin or mute Google Meet participants
• Google Meet hardware Help: Adjust your view of meeting participants in a Meet hardware room
• Google Meet hardware Help: Google Meet hardware certification program for ChromeOS peripherals & devices
• Google Workspace Admin Help: Prepare your network for Meet meetings & live streams
• Google Workspace Updates Blog: Google Meet now supports high definition video for meeting recording and devices

We're introducing new Gemini features tailored for small businesses, including a direct Google Business Profile connection and proactive Business notebooks — designed to transform the app into a partner that natively understands your brand.

Small businesses are the true engine of the global economy, yet entrepreneurs often find themselves stretched thin, playing the roles of CEO, CMO and customer service team all before lunch. AI holds incredible promise to act as an extension of your team, but to be truly helpful, it needs to remember your brand voice and context so you don't have to re-explain your goals every time you log in.

Building on the new Google AI capabilities we announced in May, we’re excited to share what’s next for Gemini and Google Business Profile users. Today on stage at Google for Brazil, we introduced new Gemini app features specifically designed for business owners everywhere.

Rolling out globally this month, these updates transform Gemini into a deeply knowledgeable, in-pocket partner that natively understands your business and helps you get more done.

Connect your Google Business Profile to Gemini

Your Google Business Profile serves as your digital storefront, helping you stand out on Google Search and Maps, build instant credibility through customer reviews, and turn online searches into customer actions like bookings, orders and sales. That’s why we’re introducing new business features in Gemini that connect directly to the tools you already use to run your business, starting with Google Business Profile.

In the coming weeks, you’ll be able to securely connect your Google Business Profile to Gemini with a single tap. Once connected, Gemini becomes an AI assistant that actually knows your business, having access to your real-world context like customer reviews, customer questions and performance data.

This gives Gemini all the context it needs to provide recommendations and content that’s relevant to your business, and allows you to offload complex, time consuming tasks:

• Turn insights into action: Ask, “how did my business do this month?” and Gemini can analyze your actual search impressions, direction requests, call data and customer engagement.
• Seamless review management: Ask, “help me respond to my latest review,” and it can draft a highly tailored response in your brand's voice, referencing the specific feedback the customer left.
• Real-time profile updates: Ask Gemini to update your operating hours, post seasonal updates or identify gaps in your profile seamlessly.

Stay ahead with Business notebooks

Organization and timing are everything when you're running a business. To give owners a centralized hub to manage their workflows, we’re introducing Business notebooks.

Notebooks serve as a focused space where you can organize your chats, sources and now your Google Business Profile and website. Gemini is able to reference this information so you can pick up your conversations right where you left off. Beyond just keeping things organized, the core value of this knowledge base is its grounding in your unique context. With this understanding, you can quickly analyze business trends, generate creative assets that match your brand and use Gemini to brainstorm your next idea based on your customer reviews.

Business notebooks also proactively surface key insights and recommend actionable steps the moment you open it.

What's waiting for you in your Business notebook:

• Proactive alerts: See critical action items, like an unanswered customer question or holiday hours that haven't been set yet.
• Tailored recommendations: Discover new market opportunities and receive grounded suggestions to optimize your daily operations, such as pricing or positioning for products based on the local market.
• Streamlined execution: Move quickly from ideation to action. You can develop creative concepts for promotional campaigns and analyze your performance metrics.

The Google Business Profile integration and Business notebooks will begin rolling out globally this month. We want to make it as easy as possible for every small business owner to use the best of our AI to grow, so keep an eye out for special Workspace and Gemini offers coming soon. In the meantime, open the Gemini app today to connect your Business Profile and experience AI built specifically for your business needs.

Gemini 3.5 Live Translate

Gemini 3.5 Live Translate is our latest audio model, delivering near real-time speech-to-speech translation in over 70 languages.

Twenty years ago, translation at Google began as one of our pioneering machine learning experiments to turn the science of language into the magic of human connection. That experiment has come a long way with over a trillion words being translated for billions of users across our products every month.

Today, we’re taking our next step with the release of Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation.

The model automatically detects 70+ languages and generates smooth, natural-sounding translated speech that preserves the speakers' intonation, pacing and pitch. Unlike turn by turn systems that wait for the speaker to finish speaking before responding, 3.5 Live Translate generates speech continuously, balancing the trade-off between waiting for context to improve quality and translating immediately to stay in sync with the speaker. It delivers fluid audio without awkward pauses and stays just a few seconds behind the speaker throughout the session.

Gemini 3.5 Live Translate is rolling out starting today across Google products:

• For developers in public preview via the Gemini Live API and Google AI Studio
• For enterprises in private preview starting this month in Google Meet
• For everyone via Google Translate on Android and iOS

Build with 3.5 Live Translate

Gemini 3.5 Live Translate processes speech as it’s streamed, enabling a more seamless connection across languages. The model handles multilingual inputs without the need to manually configure settings. At the same time, its noise robustness ensures applications can handle loud, unpredictable environments. You can use its capabilities to help facilitate live interpretation for multilingual calls, meetings, lessons, broadcasts and more.

Watch the Gemini Live API in action, enabling dubbing and simultaneous multi-language translation. Dive into the demo or more example code in the Gemini Cookbook.

By utilizing the Gemini Live API, developer platforms like Agora, Fishjam, LiveKit, Pipecat, and Vision Agents enable developers to build and deploy voice translation apps with ease. These integrations handle the complex real-time media streaming infrastructure, so developers can focus on the user experience.

Our partners at Grab are testing the model to enable multilingual communication in near real-time between drivers and travelers at pickups. These users make over 10 million voice calls per month through Grab.

See how Grab has been testing 3.5 Live Translate to transform communication between users.

Read the early reviews

In addition to Grab, companies like CJ ENM, LiveKit and others have shared positive feedback on 3.5 Live Translate highlighting its impressive translation quality, accuracy and low latency:

While testing Gemini 3.5 Live Translate, we’ve valued its ability to auto-detect multiple languages and translate speech accurately with low latency.

Philipp Kandal
Chief Product Officer at Grab

Experience 3.5 Live Translate in your video meetings

Speech translation in Google Meet will soon use 3.5 Live Translate, improving the experience by:

• Offering 70+ languages, an improvement from the previous limit of just five languages,
• Enabling conversations across over 2000+ language combinations in one meeting, expanding from the previous state of only translating to and from English,
• Updating the interface to provide instant access to speech translation.

We’re launching this update in private preview for select business Google Workspace customers starting this month, followed by a broader rollout later this year.

Google Meet participants use speech translation to communicate across English, Mandarin, and Swedish.

Get 3.5 Live Translate in the Google Translate app on Android or iOS

The model is also rolling out on the Google Translate app globally, on both Android and iOS. When using the Live translate feature, simply connect any pair of headphones to experience a more seamless translation that mirrors the speaker’s tone across 70+ languages.

For Android users, we’re also starting to roll out a new ‘listening mode’ with 3.5 Live Translate that lets you hear translations directly through your phone’s earpiece. Simply hold your phone to your ear just like a regular call, and the translated audio streams straight to you. This new experience can be helpful in situations where you want to quickly hear translations without others hearing, and you don’t have your headphones handy.

Using the new listening mode, users can hear a near real-time English translation of a guided tour in Spanish directly through their phone's earpiece.

Watermarked with SynthID

All audio generated by our models is watermarked with SynthID. This imperceptible watermark is woven directly into the audio output, ensuring AI-generated content remains detectable to help prevent misinformation. For details on our approach to safety and responsibility, review the model card.

Google tools like AI Mode in Search, Maps, Waze and the Gemini app can help guide you from the first whistle to the final goal.

As the popular soccer tournament kicks off across North America, Google is making it easier for you to follow every moment no matter where you are. Whether you’re searching for the latest scores, navigating your way to a match or looking for a recap of the day's biggest plays, Search, Maps, Waze and the Gemini app can help bring you closer to the action.

1. Get real-time info on Search.

Now, when you search for soccer, it’s even easier to quickly access real-time information about the game, like visuals for live scores, lineups, standings, brackets, stories and social content. For example, if you’re looking up Mexico vs. South Africa mid-match, you can see each team's score, standings and a carousel of other live match info. You can even pin a match’s live score to your iOS or Android device’s lock screen by following a specific match or team. You’ll receive live updates before and after each game.

2. Dive deep into the details with AI Mode in Search.

You can use AI Mode in Search for everything from agentic ticket booking to asking complex questions around rules, players, teams and more.

Say you’re trying to learn about different types of soccer formations and when coaches might use each one. You can ask AI Mode to create an interactive visual that’s tailored to your specific question. These generative UI capabilities are currently available for AI Mode Pro and Ultra subscribers and will be available for everyone in Search this summer, free of charge.

3. Make game-time decisions with Maps and Waze.

Google Maps and Waze will have the latest information about traffic, road closures, pedestrian zones, transit routes and more so you can feel confident navigating the games. We even updated Street View imagery of many stadiums that are hosting matches, so you can visualize the area before you get there. And for the first time on Waze, you can see live score updates at a glance whenever your car is stopped.

If you don't have tickets to the stadium, Google Maps can help you track down the perfect viewing party nearby. Just Ask Maps something like, “Find me a reservation for 4 at 7:30 p.m., somewhere I can watch the World Cup match and meet other fans."

4. Take your fandom further with Gemini.

The Gemini app can now reference match information about live soccer games and news providing the latest scores, highlights, standings and more as the action unfolds. For certain topics, Gemini can generate new visual elements — such as stats, images and videos highlighting up-to-date information on the latest action across soccer games — transforming standard text responses into a visual, dynamic matchday hub.

You can even turn yourself into a player on your favorite team with new Nano Banana templates designed to let fans put themselves directly into the action. Just upload a photo to these custom scenes to picture yourself celebrating in the stadium or scoring an incredible goal while wearing your country’s colors or official jersey. These templates are rolling out globally in the coming days in Gemini. Find them in the new Images tab on the navigation menu or from your Gemini homescreen when clicking the + then “Create image” in the prompt bar.

If you're a Plus, Pro or Ultra subscriber, you can use Scheduled Actions in the Gemini app to get caught up on the action with a morning briefing on international soccer news. You can customize this daily digest to focus on your teams and favorite players, then receive match updates, scores and an overall summary automatically at a time and frequency you choose.

To set it up, just click “Settings” within Gemini, open “Scheduled actions” and head to the soccer news digest template. It’s an easy way to make sure you never miss a moment of the tournament.

What's Changed

• fix(core): harden PTY resize against native crashes by @scidomino in #27496
• Changelog for v0.45.0-preview.0 by @gemini-cli-robot in #27495
• Changelog for v0.44.0 by @gemini-cli-robot in #27569
• fix(cli): prevent spam loop when preferredEditor is invalid by @Niralisj in #25324
• Adding quote by @scidomino in #27571
• Transition to flash GA model when experiment flag is present. by @DavidAPierce in #27570
• chore(ci): add optimized PR size labeler and batch workflows by @sripasg in #27616
• fix(ci): use pull_request_target trigger to grant write access on fork PRs by @sripasg in #27637
• fix(patch): cherry-pick e4315b3 to release/v0.46.0-preview.0-pr-27645 to patch version v0.46.0-preview.0 and create version 0.46.0-preview.1 by @gemini-cli-robot in #27655
• fix(patch): cherry-pick f40498d to release/v0.46.0-preview.1-pr-27676 to patch version v0.46.0-preview.1 and create version 0.46.0-preview.2 by @gemini-cli-robot in #27699
• fix(patch): cherry-pick f08b4af to release/v0.46.0-preview.2-pr-27749 to patch version v0.46.0-preview.2 and create version 0.46.0-preview.3 by @gemini-cli-robot in #27768

Full Changelog: v0.45.3...v0.46.0

Building on our October launch, Gemini in Google Classroom can now help educators more easily convert rubric files and images into Google Classroom rubrics, right within the assignment creation workflow. Educators can now upload more file types, such as .jpeg and .png files. For example, by uploading a photo of a physical rubric or using existing files, Gemini in Classroom can help educators quickly generate structured, interactive rubrics within the Classroom interface. They can then make edits to the converted rubric before saving it. This Gemini-powered automation reduces manual data entry and helps educators maintain consistent grading standards across their assignments.

With this launch, rubric conversion will be controlled by the Gemini in Classroom setting in the Admin console. If Gemini in Classroom is disabled for your organization, you’ll no longer be able to convert rubrics from documents or images.

This feature is only available in English for users over age 18.

Getting started

• Admins: This feature will be available by default if Gemini in Classroom is enabled. Visit the Help Center to learn more about managing access to Gemini in Classroom.
• End users: Visit the Help Center to learn more about creating and reusing rubrics for an assignment.

Rollout pace

• Rapid Release and Scheduled Release domains: Full rollout (1–3 days for feature visibility) starting on June 8, 2026

Availability

• Education: Education Fundamentals, Standard, and Plus

Resources

• Google Help: Create or reuse a rubric for an assignment
• Google Workspace Updates Blog: Educators can now convert rubrics in Google Classroom from Drive or local files with help from Gemini
• Keyword: Manage access to Gemini in Classroom

Google Drive is introducing alignment approvals, a lightweight mechanism that allows teams to request and record document sign-offs without file changes resetting the approval flow. When a document is in a partially approved state, collaborators can continue making edits without resetting any recorded approver decisions.

Alignment approvals can be initiated via a new checkbox within the standard request dialog across web clients.

When checked, "Require all approvers to review the same content" resets pending approvals if the file content changes. This is the default behavior.

When unchecked, changes to the file content don't reset pending approvals.

This feature serves use cases where strict content locking is unnecessary, making it easier for teams to maintain momentum on fluid projects. While an approval remains pending, individual approvers retain the flexibility to manually reset their approved status back to pending if subsequent content edits no longer match their expectations.

This update follows a series of recent enhancements to the Drive approvals ecosystem, including programmatic approval management with the Drive API.

Getting started

• Admins: Approval requests are enabled by default and can be disabled at the domain, OU, and group level. There is no admin setting that controls alignment approvals specifically; users can access them if they have access to the broader approval request feature. Visit the Help Center to learn more about managing Drive approvals.
• End users: Alignment approvals will be off by default and can be enabled by the user. Visit the Help Center to learn more about getting approvals in Drive.

Rollout pace

• Rapid Release domains: Gradual rollout (up to 15 days for feature visibility) started on June 2, 2026
• Scheduled Release domains: Full rollout (1–3 days for feature visibility) starting on June 15, 2026

Availability

• Business: Business Standard and Plus
• Enterprise: Enterprise Starter, Standard, and Plus
• Education: Education Plus
• Other Editions: Enterprise Essentials and Enterprise Essentials Plus; Nonprofits
• Education Add-ons: Teaching and Learning

Resources

• Google Workspace Admin Help: Manage approvals
• Google Drive Help: Get approvals on files in Google Drive
• Google Workspace Developer Documentation: Manage approvals

Gemini 3.5 Live Translate is our latest audio model, delivering near real-time speech-to-speech translation in over 70 languages.

Twenty years ago, translation at Google began as one of our pioneering machine learning experiments to turn the science of language into the magic of human connection. That experiment has come a long way with over a trillion words being translated for billions of users across our products every month.

Today, we’re taking our next step with the release of Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation.

The model automatically detects 70+ languages and generates smooth, natural-sounding translated speech that preserves the speakers' intonation, pacing and pitch. Unlike turn by turn systems that wait for the speaker to finish speaking before responding, 3.5 Live Translate generates speech continuously, balancing the trade-off between waiting for context to improve quality and translating immediately to stay in sync with the speaker. It delivers fluid audio without awkward pauses and stays just a few seconds behind the speaker throughout the session.

Gemini 3.5 Live Translate is rolling out starting today across Google products:

• For developers in public preview via the Gemini Live API and Google AI Studio
• For enterprises in private preview starting this month in Google Meet
• For everyone via Google Translate on Android and iOS

Build with 3.5 Live Translate

Gemini 3.5 Live Translate processes speech as it’s streamed, enabling a more seamless connection across languages. The model handles multilingual inputs without the need to manually configure settings. At the same time, its noise robustness ensures applications can handle loud, unpredictable environments. You can use its capabilities to help facilitate live interpretation for multilingual calls, meetings, lessons, broadcasts and more.

Watch the Gemini Live API in action, enabling dubbing and simultaneous multi-language translation. Dive into the demo or more example code in the Gemini Cookbook.

By utilizing the Gemini Live API, developer platforms like Agora, Fishjam, LiveKit, Pipecat, and Vision Agents enable developers to build and deploy voice translation apps with ease. These integrations handle the complex real-time media streaming infrastructure, so developers can focus on the user experience.

Our partners at Grab are testing the model to enable multilingual communication in near real-time between drivers and travelers at pickups. These users make over 10 million voice calls per month through Grab.

See how Grab has been testing 3.5 Live Translate to transform communication between users.

Read the early reviews

In addition to Grab, companies like CJ ENM, LiveKit and others have shared positive feedback on 3.5 Live Translate highlighting its impressive translation quality, accuracy and low latency:
"While testing Gemini 3.5 Live Translate, we’ve valued its ability to auto-detect multiple languages and translate speech accurately with low latency." — Philipp Kandal, Chief Product Officer at Grab

Experience 3.5 Live Translate in your video meetings

Speech translation in Google Meet will soon use 3.5 Live Translate, improving the experience by:

• Offering 70+ languages, an improvement from the previous limit of just five languages,
• Enabling conversations across over 2000+ language combinations in one meeting, expanding from the previous state of only translating to and from English,
• Updating the interface to provide instant access to speech translation.

We’re launching this update in private preview for select business Google Workspace customers starting this month, followed by a broader rollout later this year.

Google Meet participants use speech translation to communicate across English, Mandarin, and Swedish.

Get 3.5 Live Translate in the Google Translate app on Android or iOS

The model is also rolling out on the Google Translate app globally, on both Android and iOS. When using the Live translate feature, simply connect any pair of headphones to experience a more seamless translation that mirrors the speaker’s tone across 70+ languages.

For Android users, we’re also starting to roll out a new ‘listening mode’ with 3.5 Live Translate that lets you hear translations directly through your phone’s earpiece. Simply hold your phone to your ear just like a regular call, and the translated audio streams straight to you. This new experience can be helpful in situations where you want to quickly hear translations without others hearing, and you don’t have your headphones handy.

Using the new listening mode, users can hear a near real-time English translation of a guided tour in Spanish directly through their phone's earpiece.

Watermarked with SynthID

All audio generated by our models is watermarked with SynthID. This imperceptible watermark is woven directly into the audio output, ensuring AI-generated content remains detectable to help prevent misinformation. For details on our approach to safety and responsibility, review the model card.

Gemma 4 12B is designed to bring high-performance multimodal intelligence directly to your laptop, combining mobile-first efficiency with advanced reasoning.

Today, we are introducing Gemma 4 12B, our latest model designed to bring agentic multimodal intelligence directly to laptops. Bridging the gap between our edge-friendly E4B and our more advanced 26B Mixture of Experts (MoE), Gemma 4 12B packages powerful capabilities inside a reduced memory footprint. It is also our first mid-sized model to feature native audio inputs.

Thanks to the developer community, Gemma 4 models have now crossed 150 million downloads. You’ve built everything from wearable robotic arms for physical assistance to enterprise-grade AI security. We're excited to see what you build with this latest addition.

Here’s an overview of what makes Gemma 4 12B unique:

• Novel unified architecture: No multimodal encoders. The vision and audio inputs flow directly into the LLM backbone.
• Advanced reasoning: Benchmark performance nearing our 26B model, unlocking powerful multi-step reasoning and agentic workflows.
• Laptop ready: Small enough to run locally with just 16GB of VRAM or unified memory.
• Open and accessible: Released under an Apache 2.0 license with support across the developer ecosystem.
• Drafter-ready: Gemma 4 12B comes equipped with Multi-Token Prediction (MTP) drafters to reduce latency.

Together, these features bring advanced multimodal capabilities to everyday hardware without sacrificing speed or reasoning. Let's now take a closer look at how Gemma 4 12B achieves this.

Run state-of-the-art agents locally

Gemma 4 12B delivers performance nearing our larger 26B MoE model on standard benchmarks, but at less than half the total memory footprint. Small enough to run locally on consumer laptops with 16GB of RAM, it unlocks powerful multimodal and agentic experiences right on your machine.

Experience a uniquely efficient, unified architecture

What makes Gemma 4 12B stand out is its streamlined approach to processing visual and audio inputs. Traditional multimodal models typically rely on separate encoders to translate images and audio before passing those representations to the language model. Because these split encoders add latency and increase memory usage, we trained Gemma 4 12B with an encoder-free architecture to integrate audio and vision input directly.

Here is how Gemma 4 12B processes multimodal inputs natively:

• Vision: We replaced Gemma 4’s vision encoder with a lightweight embedding module consisting of a single matrix multiplication, positional embedding and normalizations. This allows the LLM backbone to take over visual processing.
• Audio: We simplified audio processing even further. We removed the audio encoder entirely and projected the raw audio signal into the same dimensional space as text tokens.

For developers who want a breakdown, head over to our companion Gemma 4 12B Developer Guide.

See native audio processing in action: Watch Gemma 4 12B transcribe, format, and translate voice inputs entirely offline using the Google AI Edge Eloquent app.

Get started today

• Try it yourself: Experiment with a couple of clicks in LM Studio, Ollama, Google AI Edge Gallery App, the Google AI Edge Eloquent app and the LiteRT-LM CLI
• Download the weights: Download the pre-trained and instruction-tuned checkpoints directly from Hugging Face and Kaggle.
• Integrate & learn: Review the developer documentation and the quick start notebook.
• Use your favorite development tools: Implement local inference pipelines with Hugging Face Transformers, llama.cpp, MLX, SGLang, and vLLM, or fine-tune with efficiency using Unsloth.
• Unlock Agentic Development with Gemma Skills: To support agents to build with the latest Gemma advancements, we are releasing our official Skills Repository. This is a library of skills designed specifically to enable agents to build with Gemma models.
• Deploy your way: Spin up endpoints in production using Google Cloud. Deploy your way through Gemini Enterprise Agent Platform Model Garden, Cloud Run, and GKE.