← Back to results

menu Main menu move to sidebar hide Navigation Main page Contents Current events Random article About Wikipedia Contact us Contribute Help Learn to edit Community portal Recent changes Upload file Special pages Search Search Appearance Donate Create account Log in Personal tools Donate Create account Log in Contents move to sidebar hide (Top) 1 History 2 Overview Toggle Overview subsection 2.1 Architecture 2.2 Variants 3 See also 4 References 5 External links Toggle the table of contents Gemma (language model) 9 languages Čeština Español Ido 日本語 한국어 Polski Русский ไทย Türkçe Edit links Article Talk English Read Edit View history Tools Tools move to sidebar hide Actions Read Edit View history General What links here Related changes Upload file Permanent link Page information Cite this page Get shortened URL Print/export Download as PDF Printable version In other projects Wikidata item Appearance move to sidebar hide From Wikipedia, the free encyclopedia Family of large language models by Google Gemma Developer Google DeepMind Release February 21, 2024 &#59; 2 years ago  ( 2024-02-21 ) [ 1 ] Stable release Gemma 4 / April 2, 2026 &#59; 2 months ago  ( 2026-04-02 ) [ 2 ] Type Large language model License Gemma 4: Apache 2.0 Gemma 3 and earlier: Source-available (Gemma Terms of Use) [ 3 ] Website deepmind .google /models /gemma / Gemma is a series of source-available large language models developed by Google DeepMind . It is based on similar technologies as Gemini . [ 4 ] The first version was released in February 2024, followed by Gemma 2 in June 2024, Gemma 3 in March 2025, and the free and open-source Gemma 4 in April 2026. Variants of Gemma have also been developed, such as the vision-language model PaliGemma and the model MedGemma for medical consultation topics. History [ edit ] In February 2024, Google debuted Gemma, a collection of source-available LLMs that serve as a lightweight version of Gemini. The initial release came in two sizes: neural networks with two and seven billion parameters respectively. Multiple publications viewed this as a response to competitors such as Meta releasing source code for their AI models, and a shift from Google's longstanding practice of keeping its AI source code private. [ 5 ] [ 6 ] [ 7 ] [ 8 ] Gemma 2 was released on June 27, 2024, [ 9 ] and Gemma 3 was released on March 12, 2025. [ 10 ] [ 11 ] On April 2, 2026, Google released Gemma 4 under the free and open-source Apache 2.0 license. [ 2 ] [ 12 ] Overview [ edit ] Based on similar technologies as the Gemini series of models, Gemma is described by Google as helping support its mission of "making AI helpful for everyone". [ 13 ] Google offers official Gemma variants optimized for specific use cases, such as MedGemma for medical analysis. [ 14 ] Since its release, Gemma models have had over 150 million downloads, with 70,000 variants available on Hugging Face . [ 15 ] Gemma 3 was offered in 1, 4, 12, and 27 billion parameter sizes with support for over 140 languages. As multimodal models, they support both text and image input. [ 16 ] Google also offers Gemma 3n –  smaller models optimized for execution on consumer devices like smartphones, laptops, and tablets. [ 17 ] The latest generation of models is Gemma 4, released on April 2, 2026. It is available in four sizes: Effective 2B (E2B), Effective 4B (E4B), 26B Mixture of Experts (MoE), and 31B Dense. Gemma 4 supports multimodal input, including images and video across all models, with native audio input on the E2B and E4B models. [ 18 ] [ 19 ] Gemma 4's 31B Dense variant reached third place on Arena 's text leaderboard, and the 26B variant reached sixth place. [ 19 ] Gemma 4 12B was released on June 3, 2026 and features a unified multimodal architecture that processes images and audio without encoders. [ 20 ] Architecture [ edit ] Gemma 3 is based on a decoder-only transformer architecture with grouped-query attention (GQA) and the SigLIP vision encoder. Every model has a context length of 128K, with the exception of Gemma 31B, which has a context length of 32K. [ 21 ] Quantized versions fine-tuned using quantization-aware training (QAT) are also available, [ 21 ] offering sizable memory usage improvements with some negative impact on accuracy and precision. [ 22 ] Variants [ edit ] Google develops official variants of Gemma models designed for specific purposes, like medical analysis or programming. These include: CodeGemma (2B and 7B): CodeGemma is a group of models designed for code completion as well as general coding use. [ 23 ] It supports multiple programming languages, including Python , Java , C++ , and more. [ 24 ] DolphinGemma (roughly 400M): Developed in collaboration with researchers at Georgia Tech and the Wild Dolphin Project, DolphinGemma aims to better understand dolphin communication through audio analysis . However, no model or data have been publicly released. [ 25 ] [ 26 ] MedGemma (4B and 27B): Also based on Gemma 3, MedGemma is designed for medical applications like image analysis. However, Google also notes that MedGemma "isn't yet clinical grade". [ 27 ] Developers at Tap Health in Gurgaon, India, have used MedGemma to enhance AI-assisted diabetes management applications. [ 28 ] PaliGemma (3B, 10B and 28B, based on Gemma 2 with 2B, 9B and 27B, respectively): For machine vision and image analysis. [ 29 ] ShieldGemma 2 (4B): Based on the Gemma 3 family, ShieldGemma is designed to identify and filter violent, dangerous, and sexually explicit images. [ 30 ] TranslateGemma (4B, 12B and 27B): For machine translation . [ 31 ] Technical specifications of Gemma models Generation Release date Parameters Context length Multimodal License Notes Gemma 1 2024-02-21 2B, 7B 8,192 No Source-available (Gemma Terms of Use) [ 3 ] 2B distilled from 7B. 2B uses multi-query attention while 7B uses multi-head attention. CodeGemma 2B, 7B 8,192 Gemma 1 fine-tuned for code generation. RecurrentGemma 2024-04-11 2B, 9B Unlimited (trained on 8,192) Griffin-based, instead of transformer-based. [ 32 ] Gemma 2 2024-06-27 2B, 9B, 27B 8,192 27B trained from web documents, code, science articles. Gemma 2 9B was distilled from 27B. Gemma 2 2B was distilled from a 7B model that remained unreleased. Uses Grouped-Query Attention. [ 33 ] PaliGemma 2024-07-10 3B 8,192 Image A vision-language model that takes text and image inputs, and outputs text. It is made by connecting a SigLIP -So400m image encoder with Gemma v1.0 2B. [ 34 ] [ 35 ] PaliGemma 2 2024-12-04 3B, 10B, 28B 8,192 Made by mating SigLIP-So400m with Gemma v2.0 2B, 9B, and 27B. Capable of more vision-language tasks. [ 36 ] [ 37 ] Gemma 3 2025-03-12 1B, 4B, 12B, 27B 131,072 All models trained with distillation. Post-training focuses on math, coding, chat, instruction following, and multilingual (supports 140 languages). Capable of function calling. 1B is not capable of vision. [ 38 ] Gemma 4 2026-04-02 31B, 26B A4B, 12B, 4B, ~2B 128K (edge) 256K (larger) Yes (vision, audio) Apache 2.0 The 31B and 26B A4B models are not capable of audio. [ 39 ] Note: open-weight models can have their context length rescaled at inference time. With Gemma 1, Gemma 2, PaliGemma, and PaliGemma 2, the cost is a linear increase of kv-cache size relative to context window size. With Gemma 3, there is an improved growth curve due to the separation of local and global attention. With RecurrentGemma, the memory use is unchanged after 2,048 tokens. See also [ edit ] List of large language models Lists of open-source artificial intelligence software References [ edit ] ^ Banks, Jeanine; Warkentin, Tris (February 21, 2024). "Gemma: Introducing new state-of-the-art open models" . The Keyword . Retrieved August 16, 2025 . ^ a b "Gemma 4: Byte for byte, the most capable open models" . Google . April 2, 2026 . Retrieved April 2, 2026 . ^ a b "Gemma Terms of Use" . Google AI for Developers . April 1, 2026 . Retrieved April 12, 2026 . ^ "Gemma models overview" . Google AI for Developers . Retrieved June 24, 2026 . ^ Khan, Jeremy (February 21, 2024). "Google unveils new family of open-source AI models called Gemma to take on Meta and others—deciding open-source AI ain't so bad after all" . Fast Company . Archived from the original on February 21, 2024 . Retrieved February 21, 2024 . ^ Alba, Davey (February 21, 2024). "Google Delves Deeper Into Open Source with Launch of Gemma AI Model" . Bloomberg News . Archived from the original on February 21, 2024 . Retrieved February 21, 2024 . ^ Metz, Cade; Grant, Nico (February 21, 2024). "Google Is Giving Away Some of the A.I. That Powers Chatbots" . The New York Times . ISSN   0362-4331 . Archived from the original on February 21, 2024 . Retrieved February 21, 2024 . ^ Nieva, Richard (February 21, 2024). "Google's Latest AI Language Models Are Open Weight, Not Open Source" . Forbes . Retrieved April 3, 2026 . ^ "Gemma 2 is now available to researchers and developers" . Google . June 27, 2024 . Retrieved August 15, 2024 . ^ "Introducing Gemma 3: The most capable model you can run on a single GPU or TPU" . The Keyword . March 12, 2025. ^ "Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM" . Hugging Face . March 12, 2025. ^ Whitwam, Ryan (April 2, 2026). "Google announces Gemma 4 open AI models, switches to Apache 2.0 license" . Ars Technica . Retrieved April 3, 2026 . ^ Banks, Jeanine; Warkentin, Tris (February 21, 2024). "Gemma: Introducing new state-of-the-art open models" . The Keyword . Retrieved July 13, 2025 . ^ "Gemma - Google DeepMind" . Google DeepMind . Retrieved July 13, 2025 . ^ Wiggers, Kyle (May 12, 2025). "Google's Gemma AI models surpass 150M downloads" . TechCrunch . Retrieved July 13, 2025 . ^ Gosthipaty, Aritra; merve; Cuenca, Pedro; Srivastav, Vaibhav (March 12, 2025). "Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM" . Hugging Face . Retrieved July 13, 2025 . ^ "Gemma 3n model overview" . Google AI for Developers . Retrieved July 13, 2025 . ^ "Gemma 4: Byte for byte, the most capable open models" . Google . April 2, 2026 . Retrieved April 2, 2026 . ^ a b Bonifacic, Igor (April 3, 2026). "Google releases Gemma 4, a family of open models built off of Gemini 3" . Engadget . Retrieved April 5, 2026 . ^ "Introducing Gemma 4 12B: a unified, encoder-free multimodal model" . Google . June 3, 2026 . Retrieved June 9, 2026 . ^ a b Gemma Team (2025). "Gemma 3 Technical Report". arXiv : 2503.19786v1 [ cs.CL ]. ^ Clark, Bryan (May 15, 2025). "What is quantization aware training?" . IBM . Retrieved July 14, 2025 . ^ Irwin, Kate (April 10, 2024). "Google Launches Coding AIs That Could Rival Microsoft's GitHub Copilot" . PCMag . Retrieved July 15, 2025 . ^ "CodeGemma" . Google AI for Developers . Retrieved July 15, 2025 . ^ "DolphinGemma: How Google AI is helping decode dolphin communication" . Georgia Tech . Retrieved July 15, 2025 . ^ Herzing, Denise; Starner, Thad (April 14, 2025). "DolphinGemma: How Google AI is helping decode dolphin communication" . The Keyword . Retrieved July 15, 2025 . ^ "MedGemma" . Google Health AI Developer Foundations . Retrieved July 15, 2025 . ^ "MedGemma: Our most capable open models for health AI development" . Google Research Blog . October 28, 2025 . Retrieved November 4, 2025 . Developers at Tap Health in Gurgaon, India, remarked on MedGemma's superior medical grounding and potential for improving AI-assisted diabetes management. ^ "PaliGemma" . Google AI for Developers . Retrieved June 24, 2026 . ^ ShieldGemma Team (2025). "ShieldGemma 2: Robust and Tractable Image Content Moderation". arXiv : 2504.01081 [ cs.CV ]. ^ Dora (January 19, 2026). "¿Qué es TranslateGemma? Modelo de Traducción Open AI Explicado - WaveSpeed Blog" . WaveSpeedAI (in Spanish) . Retrieved June 24, 2026 . ^ Botev, Aleksandar; et al. (2024). "RecurrentGemma: Moving Past Transformers for Efficient Open Language Models". arXiv : 2404.07839v2 [ cs.LG ]. ^ Gemma Team; Riviere, Morgane; Pathak, Shreya; Sessa, Pier Giuseppe; Hardin, Cassidy; Bhupatiraju, Surya; Hussenot, Léonard; Mesnard, Thomas; Shahriari, Bobak (August 2, 2024), Gemma 2: Improving Open Language Models at a Practical Size , arXiv : 2408.00118 ^ "PaLI: Scaling Language-Image Learning in 100+ Languages" . research.google . Retrieved August 15, 2024 . ^ Beyer, Lucas; et al. (July 10, 2024). "PaliGemma: A versatile 3B VLM for transfer". arXiv : 2407.07726v2 [ cs.CV ]. ^ "Introducing PaliGemma 2 mix: A vision-language model for multiple tasks- Google Developers Blog" . developers.googleblog.com . Retrieved February 22, 2025 . ^ Steiner, Andreas; André Susano Pinto; Tschannen, Michael; Keysers, Daniel; Wang, Xiao; Bitton, Yonatan; Gritsenko, Alexey; Minderer, Matthias; Sherbondy, Anthony; Long, Shangbang; Qin, Siyang; Ingle, Reeve; Bugliarello, Emanuele; Kazemzadeh, Sahar; Mesnard, Thomas; Alabdulmohsin, Ibrahim; Beyer, Lucas; Zhai, Xiaohua (2024). "PaliGemma 2: A Family of Versatile VLMs for Transfer". arXiv : 2412.03555v1 [ cs.CV ]. ^ Team, Gemma; et al. (2025). "Gemma 3 Technical Report". arXiv : 2503.19786v1 [ cs.CL ]. ^ "google/gemma-4-31B-it" . Hugging Face . April 2, 2026 . Retrieved April 3, 2026 . External links [ edit ] Official website v t e Google AI Google Google Brain Google DeepMind Computer programs AlphaGo Versions AlphaGo (2015) Master (2016) AlphaGo Zero (2017) AlphaZero (2017) MuZero (2019) Competitions Fan Hui (2015) Lee Sedol (2016) Ke Jie (2017) In popular culture AlphaGo (2017) Other AlphaFold (2018) AlphaStar (2019) AlphaTensor (2022) AlphaDev (2023) AlphaGeometry (2024) AlphaGenome (2025) Machine learning Neural networks Inception (2014) WaveNet (2016) MobileNet (2017) Transformer (2017) EfficientNet (2019) Gato (2022) Other Quantum Artificial Intelligence Lab TensorFlow Tensor Processing Unit Generative AI Chatbots Assistant (2016) Sparrow (2022) Gemini (2023) Nano Banana (2025) Models BERT (2018) XLNet (2019) T5 (2019) LaMDA (2021) Chinchilla (2022) PaLM (2022) Imagen (2023) Gemini (2023) VideoPoet (2024) Gemma (2024) Genie (2024) Veo (2024) Other DreamBooth (2022) NotebookLM (2023) Vids (2024) Gemini Robotics (2025) Antigravity (2025) See also " Attention Is All You Need " Future of Go Summit Generative pre-trained transformer Google Labs Google Workspace Category Commons v t e Google a subsidiary of Alphabet Company Divisions AI Area 120 ATAP Brain China Cloud Platform Energy Google.org Crisis Response Registry Subsidiaries Active DeepMind Fitbit ITA Software Jigsaw Looker Mandiant Security Operations Owlchemy Labs Defunct Actifio Adscape Akwan Information Technologies Anvato Apigee BandPage Bitium BufferBox Crashlytics Dodgeball DoubleClick Dropcam Endoxon Flutter Global IP Solutions Green Throttle Games GreenBorder Gridcentric ImageAmerica Impermium Invite Media Kaltix Marratech Meebo Metaweb Neotonic Software Neverware Nik Software Orbitera Pyra Labs Quest Visual Reqwireless RightsFlow Sidewalk Labs SlickLogin Titan Aerospace Typhoon Studios Urban Engines Vicarious Viewdle Wavii Wildfire Interactive YouTube Next Lab and Audience Development Group Programs Business Groups Computing University Initiative Contact Lens Content ID CrossCheck Data Liberation Front Data Transfer Project Developer Expert DigiKavach DigiPivot Digital Garage Digital News Initiative Digital Unlocked Dragonfly Founders' Award Free Zone Get Your Business Online Google for Education Google for Health Google for Startups Living Stories Made with Code News Lab PowerMeter Privacy Sandbox Project Nightingale Project Nimbus Project Sunroof Project Zero Quantum Artificial Intelligence Lab RechargeIT Sensorvault Silicon Initiative Solve for X Street View Trusted Student Ambassador Program Vevo YouTube BrandConnect YouTube Creator Awards YouTube Select YouTube Original Channel Initiative Year in Search YouTube Rewind 2018 2019 Events AlphaGo versus Fan Hui AlphaGo versus Lee Sedol AlphaGo versus Ke Jie Android Developer Challenge Android Developer Day Android Developer Lab CNN/YouTube presidential debates Code-in Code Jam Developer Day Developers Live Doodle4Google Future of Go Summit G-Day Hash Code I/O Lunar X Prize Mapathon Science Fair Summer of Code World Chess Championship 2024 YouTube Awards YouTube Comedy Week YouTube Live YouTube Music Awards 2013 2015 YouTube Space Lab YouTube Symphony Orchestra Infrastructure 111 Eighth Avenue Android lawn statues Androidland Barges Binoculars Building Central Saint Giles Chelsea Market Chrome Zone Data centers GeoEye-1 Googleplex Ivanpah Solar Power Facility James R. Thompson Center King's Cross Mayfield Mall Pier 57 Sidewalk Toronto St. John's Terminal Submarine cables Dunant Grace Hopper Unity WiFi YouTube Space YouTube Theater People Current Krishna Bharat Vint Cerf Jeff Dean John Doerr Sanjay Ghemawat Al Gore John L. Hennessy Urs Hölzle Salar Kamangar Ray Kurzweil Ann Mather Alan Mulally Rick Osterloh Sundar Pichai (CEO) Ruth Porat (CFO) Rajen Sheth Hal Varian Neal Mohan Former Andy Bechtolsheim Sergey Brin (co-founder) David Cheriton Matt Cutts David Drummond Alan Eustace Timnit Gebru Omid Kordestani Paul Otellini Larry Page (co-founder) Patrick Pichette Eric Schmidt Ram Shriram Amit Singhal Shirley M. Tilghman Rachel Whetstone Susan Wojcicki Criticism General Censorship DeGoogle FairSearch " Google's Ideological Echo Chamber " No Tech for Apartheid Privacy concerns Street View YouTube Trade unions Alphabet Workers Union YouTube copyright issues Incidents Backdoor advertisement controversy Blocking of YouTube videos in Germany Data breach Elsagate Fantastic Adventures scandal Kohistan video case Reactions to Innocence of Muslims San Francisco tech bus protests Services outages Slovenian government incident Walkouts YouTube headquarters shooting Other Android apps April Fools' Day jokes Doodles Doodle Champion Island Games Magic Cat Academy Pac-Man Easter eggs History Gmail Search YouTube Logo Material Design Mergers and acquisitions Development Software A–C Accelerated Linear Algebra AMP Actions on Google ALTS American Fuzzy Lop Android Cloud to Device Messaging Android Debug Bridge Android NDK Android Runtime Android SDK Android Studio Angular AngularJS Antigravity Apache Beam APIs App Engine App Inventor App Maker App Runtime for Chrome AppJet Apps Script AppSheet ARCore Base Bazel BeyondCorp Bigtable BigQuery Bionic Blockly Borg Caja Cameyo Chart API Charts Chrome Frame Chromium Blink Closure Tools Cloud Connect Cloud Dataflow Cloud Datastore Cloud Messaging Cloud Shell Cloud Storage Code Search Compute Engine Cpplint D–N Dalvik Data Protocol Data Studio Dialogflow Exposure Notification Fast Pair Fastboot Federated Learning of Cohorts File System Firebase Firebase Studio Firebase Cloud Messaging FlatBuffers Flutter Freebase Gadgets Ganeti Gears Gerrit Global Cache GLOP gRPC Gson Guava Guetzli Guice gVisor GYP JAX Jetpack Compose Keyhole Markup Language Kubernetes Kythe LevelDB Lighthouse lmctfy MapReduce Mashup Editor Matter Mobile Services Namebench Native Client Neatx Neural Machine Translation Nomulus O–Z Open Location Code OpenRefine OpenSocial Optimize OR-Tools Pack PageSpeed Piper Plugin for Eclipse Polymer Programmable Search Engine Project Shield Public DNS reCAPTCHA RenderScript SafetyNet SageTV Schema.org Search Console Shell Sitemaps Skia Graphics Engine Spanner Sputnik Stackdriver Swiffy Tango TensorFlow Tesseract Test Translator Toolkit Urchin UTM parameters V8 VirusTotal VisBug Wave Federation Protocol Weave Web Accelerator Web Designer Web Server Web Toolkit Webdriver Torso WebRTC Operating systems Android Cupcake Donut Eclair Froyo Gingerbread Honeycomb Ice Cream Sandwich Jelly Bean KitKat Lollipop Marshmallow Nougat Oreo Pie 10 11 12 13 14 15 16 version history smartphones Android Automotive Android Go devices Android Things Android TV Google TV interface devices Android XR ChromeOS ChromeOS Flex ChromiumOS Fuchsia Glass OS Google TV gLinux Goobuntu Wear OS Machine learning models BERT Chinchilla DreamBooth Gemini Gemini Robotics Gemma Imagen (2023) LaMDA PaLM T5 Veo (text-to-video model) VideoPoet XLNet Neural networks EfficientNet Gato Inception MobileNet Transformer WaveNet Computer programs AlphaDev AlphaFold AlphaGeometry AlphaGo AlphaGo Zero AlphaStar AlphaZero Master MuZero Formats and codecs AAB APK AV1 iLBC iSAC libvpx Lyra Protocol Buffers Ultra HDR VP3 VP6 VP8 VP9 WebM WebP WOFF2 Programming languages Carbon Dart Go Sawzall Search algorithms Googlebot Hummingbird Mobilegeddon PageRank matrix Panda Penguin Pigeon RankBrain Domain names .app .dev .google .zip g.co google.by Typefaces Croscore Noto Product Sans Roboto Software A Aardvark Account Dashboard Takeout Ad Manager AdMob Ads AdSense Affiliate Network Alerts Allo Analytics Android Auto Android Beam Answers Apture Arts & Culture Assistant Attribution Authenticator B BebaPay BeatThatQuote.com Beam Blog Search Blogger Body Bookmarks Books Ngram Viewer Browser Sync Building Maker Bump BumpTop Buzz C Calendar Cast Catalogs Chat Checkout Chrome Chrome Apps Chrome Experiments Chrome Remote Desktop Chrome Web Store Classroom Cloud Print Cloud Search Contacts Contributor Crowdsource Currents (social app) Currents (news app) D Data Commons Dataset Search Desktop Dictionary Dinosaur Game Directory Docs Docs Editors Domains Drawings Drive Duo E Earth Etherpad Expeditions Express F Family Link Fast Flip FeedBurner fflick Fi Wireless Finance Files Find Hub Fit Flights Flu Trends Fonts Forms Friend Connect Fusion Tables G Gboard Gemini Nano Banana Gesture Search Gizmo5 Google+ Gmail Goggles GOOG-411 Grasshopper Groups H Hangouts Helpouts Home I iGoogle Images Image Labeler Image Swirl Inbox by Gmail Input Tools Japanese Input Pinyin Insights for Search J Jaiku Jamboard K Kaggle Keep Knol L Labs Latitude Lens Like.com Live Transcribe Lively M Map Maker Maps Maps Navigation Marketing Platform Meet Messages Moderator My Tracks N Nearby Share News News & Weather News Archive Notebook NotebookLM Now O Offers One One Pass Opinion Rewards Orkut Oyster P Panoramio PaperofRecord.com Patents Page Creator Pay (mobile app) Pay (payment method) Pay Send People Cards Person Finder Personalized Search Photomath Photos Picasa Picasa Web Albums Picnik Pixel Camera Play Play Books Play Games Play Music Play Newsstand Play Pass Play Services Podcasts Poly Postini PostRank Primer Public Alerts Public Data Explorer Q Question Hub Quick, Draw! Quick Search Box Quick Share Quickoffice R Read Along Reader Reply S Safe Browsing SageTV Santa Tracker Schemer Scholar Search AI Overviews Knowledge Graph SafeSearch Searchwiki Sheets Shoploop Shopping Sidewiki Sites Slides Snapseed Socratic Softcard Songza Sound Amplifier Spaces Sparrow (chatbot) Sparrow (email client) Speech Recognition & Synthesis Squared Stadia Station Store Street View Surveys Sync T Tables Talk TalkBack Tasks Tenor Tez Tilt Brush Toolbar Toontastic 3D Translate Travel Trendalyzer Trends TV U URL Shortener V Video Vids Voice Voice Access Voice Search W Wallet Wave Waze WDYL Web Light Where Is My Train Widevine Wiz Word Lens Workspace Workspace Marketplace Y YouTube YouTube Kids YouTube Music YouTube Premium YouTube Shorts YouTube Studio YouTube TV YouTube VR Hardware Pixel Smartphones Pixel (2016) Pixel 2 (2017) Pixel 3 (2018) Pixel 3a (2019) Pixel 4 (2019) Pixel 4a (2020) Pixel 5 (2020) Pixel 5a (2021) Pixel 6 (2021) Pixel 6a (2022) Pixel 7 (2022) Pixel 7a (2023) Pixel Fold (2023) Pixel 8 (2023) Pixel 8a (2024) Pixel 9 (2024) Pixel 9 Pro Fold (2024) Pixel 9a (2025) Pixel 10 (2025) Pixel 10 Pro Fold (2025) Smartwatches Pixel Watch (2022) Pixel Watch 2 (2023) Pixel Watch 3 (2024) Pixel Watch 4 (2025) Tablets Pixel C (2015) Pixel Slate (2018) Pixel Tablet (2023) Laptops Chromebook Pixel (2013–2015) Pixelbook (2017) Pixelbook Go (2019) Other Pixel Buds (2017–present) Nexus Smartphones Nexus One (2010) Nexus S (2010) Galaxy Nexus (2011) Nexus 4 (2012) Nexus 5 (2013) Nexus 6 (2014) Nexus 5X (2015) Nexus 6P (2015) Tablets Nexus 7 (2012) Nexus 10 (2012) Nexus 7 (2013) Nexus 9 (2014) Other Nexus Q (2012) Nexus Player (2014) Other Android Dev Phone Android One Cardboard Chromebit Chromebook Chromebox Chromecast Clips Daydream Fitbit Glass Liftware Liquid Galaxy Nest smart speakers Thermostat Wifi Play Edition Project Ara OnHub Pixel Visual Core Project Iris Search Appliance Sycamore processor Tensor Tensor Processing Unit Titan Security Key v t e Litigation Advertising Feldman v. Google, Inc. (2007) Rescuecom Corp. v. Google Inc. (2009) Goddard v. Google, Inc. (2009) Rosetta Stone Ltd. v. Google, Inc. (2012) Google, Inc. v. American Blind & Wallpaper Factory, Inc. (2017) Jedi Blue Antitrust European Union (2010–present) United States v. Adobe Systems, Inc., Apple Inc., Google Inc., Intel Corporation, Intuit, Inc., and Pixar (2011) Umar Javeed, Sukarma Thapar, Aaqib Javeed vs. Google LLC and Ors. (2019) United States v. Google LLC (2020) Epic Games v. Google (2021) United States v. Google LLC (2023) Intellectual property Perfect 10, Inc. v. Amazon.com, Inc. (2007) Viacom International, Inc. v. YouTube, Inc. (2010) Lenz v. Universal Music Corp. (2015) Authors Guild, Inc. v. Google, Inc. (2015) Field v. Google, Inc. (2016) Google LLC v. Oracle America, Inc. (2021) Smartphone patent wars Privacy Rocky Mountain Bank v. Google, Inc. (2009) Hibnick v. Google, Inc. (2010) United States v. Google Inc. (2012) Judgement of the German Federal Court of Justice on Google's autocomplete function (2013) Joffe v. Google, Inc. (2013) Mosley v SARL Google (2013) Google Spain v AEPD and Mario Costeja González (2014) Frank v. Gaos (2019) Other Garcia v. Google, Inc. (2015) Google LLC v Defteros (2020) Gonzalez v. Google LLC (2022) Related Concepts Beauty YouTuber BookTube BreadTube " Don't be evil " Gayglers Google as a verb Google bombing 2004 U.S. presidential election Google effect Googlefight Google hacking Googleshare Google tax Googlewhack Googlization Illegal flower tribute Objectives and key results Rooting Search engine manipulation effect Side project time Sitelink Site reliability engineering StudyTube VTuber YouTube Poop YouTuber list Products Android Booting process Custom distributions Features Recovery mode Software development Street View coverage Africa Antarctica Asia Israel Europe North America Canada United States Oceania South America Argentina Chile Colombia YouTube Copyright strike Education Features Moderation Most-disliked videos Most-liked videos Most-subscribed channels Most-viewed channels Most-viewed videos Official channel Social impact YouTube Premium original programming Other Gmail interface Maps pin Most downloaded Google Play applications Stadia games Documentaries AlphaGo Google: Behind the Screen Google Maps Road Trip Google and the World Brain The Creepy Line Books Google Hacks The Google Story Googled: The End of the World as We Know It How Google Works I'm Feeling Lucky In the Plex The MANIAC Popular culture Google Feud Google Me (film) " Google Me " (Kim Zolciak song) " Google Me " (Teyana Taylor song) Is Google Making Us Stupid? Proceratium google Matt Nathanson: Live at Google The Billion Dollar Code The Internship Where on Google Earth is Carmen Sandiego? Other " Attention Is All You Need " elgooG Generative pre-trained transformer " Me at the zoo " Predictions of the end Relationship with Wikipedia " Reunion " Robot Constitution Italics denote discontinued products . Category Outline v t e Large language models (LLMs) List of LLMs AI Companies Benchmarks List of chatbots Foundation model Generative AI Concepts Language model NLP NLG Computational linguistics Foundation model Small language model Reasoning model GPT Transformer Attention KV cache Context window Tokenization Word embedding Parameter Hyperparameter Autoregression Mixture of experts (MoE) Inference Model compression Knowledge distillation Speculative decoding PagedAttention Neural scaling law Multimodality Training, prompting, and alignment Self-supervised learning Supervised learning Fine-tuning Instruction tuning RLHF Constitutional AI AI alignment AI safety Mechanistic interpretability Prompt engineering In-context learning Chain-of-thought prompting RAG Prompt injection Adversarial machine learning Hallucination Stochastic parrot Glitch token Models Early and encoder models Word2vec Seq2seq GloVe BERT XLNet T5 GPT series GPT GPT-1 GPT-2 GPT-3 GPT-4 GPT-4.1 GPT-4.5 GPT-4o GPT-5 GPT-5.5 Codex OpenAI o1 OpenAI o3 OpenAI o4-mini Other model families BLOOM Chinchilla Claude DBRX Gemini Gemma GLM GPT-J PanGu Granite Jais LaMDA Llama Vicuna Minerva Mistral and Mixtral Nemotron PaLM Phi Qwen Xiaomi MiMo Chatbots and assistants Amazon Q ChatGPT Character.ai Claude DeepSeek Doubao Ernie Bot Gemini GLM Grok Microsoft Copilot Meta AI Perplexity AI Sparrow You.com Agents, coding, and applications AI agent Intelligent agent AutoGPT CrewAI LangChain Manus Model Context Protocol Agent2Agent OpenAI Codex Vibe coding Code generation Question answering Machine translation Text summarization Chatbot Virtual assistant LLMs in higher education Software PyTorch TensorFlow Hugging Face Inference engine llama.cpp Ollama SGLang TensorRT-LLM vLLM ONNX OpenVINO Vector database ChromaDB Deep learning software Open-source AI software Hardware and infrastructure AI data center AI accelerator GPU CUDA TPU High-bandwidth memory Benchmarks, evaluation, and detection Language model benchmark MMLU Humanity's Last Exam LMArena LLM-as-a-Judge Perplexity metric GPTZero Artificial intelligence content detection Undetectable.ai Datasets and data Data set Text corpus Common Crawl The Pile Web scraping Synthetic data Training, validation, and test data sets Organizations AI21 Labs Alibaba Group Anthropic Baidu Cohere DeepSeek EleutherAI Google DeepMind Hugging Face Meta AI Microsoft AI Mistral AI Nvidia OpenAI Technology Innovation Institute xAI People Sam Altman Dario Amodei Yoshua Bengio Aidan Gomez Demis Hassabis Geoffrey Hinton Andrej Karpathy Yann LeCun Percy Liang Christopher D. Manning Arthur Mensch Mira Murati Alec Radford Noam Shazeer Ilya Sutskever Ashish Vaswani Andrew Ng Social, economic, and governance AI boom AI bubble AI slop AI anthropomorphism AI arms race Chatbot psychosis Competition Copyright Deaths linked to chatbots Environmental impact Regulation Ethics Existential risk In education In healthcare Workplace impact Category:Large language models v t e Generative AI Concepts Autoencoder Deep learning Fine-tuning Foundation model Generative adversarial network Generative pre-trained transformer Large language model Model Context Protocol Neural network Prompt engineering Reinforcement learning from human feedback Retrieval-augmented generation Self-supervised learning Stochastic parrot Synthetic data Top-p sampling Transformer Variational autoencoder Vibe coding Vision transformer Word embedding Models Text Amazon Nova Character.ai Claude Command DeepSeek Doubao Ernie EXAONE Gemini Gemma GLM GPT ChatGPT Grok IBM Granite Kimi MAI Microsoft Copilot Mistral MiniMax Muse Spark Nemotron Perplexity Solar Poe HKChat Qwen Tencent Hy Xiaomi MiMo You.com Image Adobe Firefly Flux GPT Image Ideogram Midjourney Nano Banana Recraft Seedream Stable Diffusion Video Dream Machine Genie world model Hailuo AI Kling AI LTX Runway Gen Seedance Sora Veo Speech 15.ai Eleven Gemini Speech MiniMax Speech Music Eleven Music Endel MiniMax Music Riffusion Suno Udio Products Coding tools Claude Code Codex Cursor Devin AI GitHub Copilot Google Antigravity Replit Agents AutoGPT ChatGPT agent Claude Cowork Gemini Spark Manus MiniMax Agent OpenClaw Applications Deepfake audio Slop slopaganda Companies Aleph Alpha Anthropic Anysphere Baichuan Canva Cognition AI Cohere Contextual AI DeepSeek DeepL EleutherAI ElevenLabs Google AI DeepMind HeyGen Hugging Face Inflection AI Kuaishou Lightricks Lovable Luma Labs Meta AI Meta Superintelligence Labs Microsoft AI MiniMax Mistral AI Moonshot AI OpenAI Perplexity AI Runway Safe Superintelligence Sakana AI Salesforce Scale AI SoundHound AI SpaceXAI Stability AI StepFun Synthesia Thinking Machines Lab Upstage Xiaomi Z.ai Controversies Generative AI pornography Deepfake pornography on Grok of Taylor Swift Pause Giant AI Experiments Removal of Sam Altman from OpenAI Statement on AI Risk Tay (chatbot) Théâtre D'opéra Spatial Voiceverse NFT plagiarism Category Commons v t e Artificial intelligence (AI) History timeline Glossary Companies Projects List of open-source AI software Concepts Automated reasoning Parameter Hyperparameter Loss functions Regression Bias–variance tradeoff Double descent Overfitting Clustering Gradient descent SGD Quasi-Newton method Conjugate gradient method Backpropagation Attention Convolution Normalization Batchnorm Activation Softmax Sigmoid Rectifier Gating Weight initialization Regularization Datasets Augmentation Prompt engineering Reinforcement learning Q-learning SARSA Imitation Policy gradient Diffusion Latent diffusion model Autoregression Adversary RAG Uncanny valley RLHF Self-supervised learning Reflection Recursive self-improvement Hallucination Word embedding Vibe coding Symbolic AI Neuro-symbolic AI Applications Automated theorem proving Machine learning In-context learning Artificial neural network Deep learning Language model Large NMT Reasoning Model Context Protocol Intelligent agent AI agent Artificial human companion Humanity's Last Exam Lethal autonomous weapons (LAWs) Generative AI Weak AI Hypothetical Artificial general intelligence (AGI) Artificial superintelligence (ASI) Agent2Agent protocol Implementations Audio–visual AlexNet WaveNet Human image synthesis HWR OCR Computer vision Speech synthesis 15.ai ElevenLabs Speech recognition Whisper Facial recognition AlphaFold Text-to-image models Aurora DALL-E Firefly Flux GPT Image Ideogram Imagen Midjourney Recraft Stable Diffusion Text-to-video models Dream Machine Runway Gen Hailuo AI Kling Sora Seedance Veo Music generation Riffusion Suno Udio World models Genie Oasis Text List of large language models Project Debater IBM Watson IBM Watsonx Decisional AlphaGo AlphaZero OpenAI Five Self-driving car MuZero Action selection AutoGPT Robot control Reasoning systems Deductive classifiers Expert systems Inference engines Knowledge-based systems Logic programs Procedural reasoning systems Semantic reasoners Rule-based systems Cognitive architectures ACT-R Soar CLARION LIDA OpenCog Knowledge bases ConceptNet Wikidata DBpedia YAGO People Alan Turing Warren Sturgis McCulloch Walter Pitts John von Neumann Christopher D. Manning Claude Shannon Shun'ichi Amari Kunihiko Fukushima Takeo Kanade Marvin Minsky John McCarthy Nathaniel Rochester Allen Newell Cliff Shaw Herbert A. Simon Oliver Selfridge Frank Rosenblatt Bernard Widrow Joseph Weizenbaum Seymour Papert Seppo Linnainmaa Paul Werbos Geoffrey Hinton John Hopfield Jürgen Schmidhuber Yann LeCun Yoshua Bengio Lotfi A. Zadeh Stephen Grossberg Alex Graves James Goodnight Andrew Ng Fei-Fei Li Alex Krizhevsky Ilya Sutskever Oriol Vinyals Quoc V. Le Ian Goodfellow Demis Hassabis David Silver Andrej Karpathy Ashish Vaswani Noam Shazeer Aidan Gomez John Schulman Mustafa Suleyman Jan Leike Daniel Kokotajlo François Chollet Neural network architectures Neural Turing machine Differentiable neural computer Transformer Vision transformer (ViT) Recurrent neural network (RNN) Long short-term memory (LSTM) Gated recurrent unit (GRU) Echo state network Multilayer perceptron (MLP) Convolutional neural network (CNN) Residual neural network (RNN) Highway network Mamba Autoencoder Variational autoencoder (VAE) Generative adversarial network (GAN) Graph neural network (GNN) Political AI Cold War AI safety ( Alignment ) AI takeover Elections Ethics of AI EU AI Act Nationalism Precautionary principle Regulation of AI US Virtual politician Propaganda Social and economic AI boom AI bubble AI data center AI effect AI literacy AI slop AI veganism AI winter Anthropomorphism Arms race Competition Environmental impact Explainable AI Generative engine optimization In architecture In education In fiction In healthcare Chatbot psychosis In marketing In video games In visual art Military applications AI warfare Workplace impact Category Retrieved from " https://en.wikipedia.org/w/index.php?title=Gemma_(language_model)&oldid=1360910408 " Categories : 2024 software 2024 in artificial intelligence Chatbots Generative pre-trained transformers Google DeepMind Google software Large language models Multimodal interaction Hidden categories: CS1 Spanish-language sources (es) Articles with short description Short description matches Wikidata Use mdy dates from April 2026 This page was last edited on 24 June 2026, at 12:21  (UTC) . Text is available under the Creative Commons Attribution-ShareAlike 4.0 License ; additional terms may apply. By using this site, you agree to the Terms of Use and Privacy Policy . Wikipedia® is a registered trademark of the Wikimedia Foundation, Inc. , a non-profit organization. Privacy policy About Wikipedia Disclaimers Contact Wikipedia Legal & safety contacts Code of Conduct Developers Statistics Cookie statement Mobile view Search Search Toggle the table of contents Gemma (language model) 9 languages Add topic