https://deepmind.google/models/gemma/gemma-4/ Skip to main content Explore our next generation AI systems Explore models Gemini [nav__dm__g] Gemini Learn, build, and plan anything [nav__dm__n] Nano Banana Create and edit detailed images [nav__dm__g] Gemini Audio Talk, create and control audio Specialized models [nav__dm__v] Veo Generate cinematic video with audio [nav__dm__i] Imagen Generate high-quality images from text [nav__dm__l] Lyria Generate high fidelity music and audio World models & embodied AI [nav__dm__g] Genie 3 Generate and explore interactive worlds [nav__dm__g] Gemini Robotics Perceive, reason, use tools and interact Open models [nav__dm__g] Gemma Build responsible AI applications at scale Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs [nav__dm__s] SIMA 2 An agent that plays, reasons, and learns with you [nav__dm__g] Genie 3 Generate and explore interactive worlds [nav__dm__a] AlphaGo Mastering the game of Go [nav__dm__g] Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Unlocking a new era of discovery with AI Explore science Life sciences [nav__dm__a] AlphaFold Predict protein structures with high accuracy [nav__dm__a] AlphaGenome Decode genetics to pinpoint diseases [nav__dm__a] AlphaMissense Find root causes of rare genetic diseases Climate and sustainability [nav__dm__a] AlphaEarth Foundations Map our planet in unprecedented detail [nav__dm__w] WeatherNext Fast and accurate AI weather forecasting [nav__dm__w] Weather Lab Test our experimental weather models Our mission is to build AI responsibly to benefit humanity About Google DeepMind Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We're looking for people who want to make a real, positive impact on the world Education We work to make AI more accessible to the next generation Our National Partnerships for AI Working with governments worldwide to benefit people through frontier AI The Podcast Join Professor Hannah Fry as she uncovers the extraordinary way AI is transforming our world Models Explore our next generation AI systems Explore models Gemini [nav__dm__g] Gemini Learn, build, and plan anything [nav__dm__n] Nano Banana Create and edit detailed images [nav__dm__g] Gemini Audio Talk, create and control audio Specialized models [nav__dm__v] Veo Generate cinematic video with audio [nav__dm__i] Imagen Generate high-quality images from text [nav__dm__l] Lyria Generate high fidelity music and audio World models & embodied AI [nav__dm__g] Genie 3 Generate and explore interactive worlds [nav__dm__g] Gemini Robotics Perceive, reason, use tools and interact Open models [nav__dm__g] Gemma Build responsible AI applications at scale Research Our latest AI breakthroughs and updates from the lab Explore research Breakthroughs [nav__dm__s] SIMA 2 An agent that plays, reasons, and learns with you [nav__dm__g] Genie 3 Generate and explore interactive worlds [nav__dm__a] AlphaGo Mastering the game of Go [nav__dm__g] Gemini Robotics Perceive, reason, use tools and interact Learn more Evals Publications Responsibility Science Unlocking a new era of discovery with AI Explore science Life sciences [nav__dm__a] AlphaFold Predict protein structures with high accuracy [nav__dm__a] AlphaGenome Decode genetics to pinpoint diseases [nav__dm__a] AlphaMissense Find root causes of rare genetic diseases Climate and sustainability [nav__dm__a] AlphaEarth Foundations Map our planet in unprecedented detail [nav__dm__w] WeatherNext Fast and accurate AI weather forecasting [nav__dm__w] Weather Lab Test our experimental weather models About Our mission is to build AI responsibly to benefit humanity About Google DeepMind Responsibility Ensuring AI safety through proactive security, even against evolving threats News Discover our latest AI breakthroughs, projects, and updates Careers We're looking for people who want to make a real, positive impact on the world Education We work to make AI more accessible to the next generation Our National Partnerships for AI Working with governments worldwide to benefit people through frontier AI The Podcast Join Professor Hannah Fry as she uncovers the extraordinary way AI is transforming our world Build with Gemini Try Gemini Google DeepMind DeepMind Google AI Learn about all our AI Google DeepMind Explore the frontier of AI Google Labs Try our AI experiments Google Research Explore our research Products and apps Gemini app Chat with Gemini Google AI Studio Build with our next-gen AI models Google Antigravity Our agentic development platform Models Research Science About Build with Gemini Try Gemini Gemma 4 Our most intelligent open models, built from Gemini 3 research and technology to maximize intelligence-per-parameter Read docs Try in Google AI Studio [-pT0obGj4NI3YcivFrLZ63AQDh4VNe6TgS8IzpAx-z9O3LUTKYuec_GeM2WDHuB0VtmjvlcO8Gwyb_XUQf-ol8WYbInLE3xlXhrs7VnmET0Fk2g] [9niq7sKOnvFUhmkPb_QYGSj4CMb-jo7TW86H54-lJXaUoXvcDx_Y5YJ52sZZATVgFw9xKmOQA1aEBPX3tn-KZ-8KZA2zZtm14o2ztm1zG7K0bkCL0Eg] Model sizes Slide 1 of 2 [241kUbfd5jozU-ETxthrBSW7_xgCEvMzxVVuThwIzazfHluocz1svdDFjkXpZjNqbGEwMCJDtwa9u9QJAjgOfa5Y8-ss43U4yClrEY241305bqThgbU] [LoBNGAVAJpiKOwh-79dLSX_swo_0DOrHKQ4pxZ_TaD5NzTtTIsaQ6wnglBvW8gvyPVd1tMLPVeqKtbVW8z-n3_3SDy_e3A9DZwFvBvDhgxl40OPDTg] Your browser does not support the video tag. Your browser does not support the video tag. E2B & E4B Maximum compute and memory efficiency A new level of intelligence for mobile and IoT devices Learn more [c9w8JGekqO0jTMuXmWjsS9bZJVlNKAl1F5rJmg-emLQkQul5PNmENZosqnmp7kmRWTz0XsmIFK1BVob56zvgb9fw_9NmX4yDCDMrJ442CB9bKNRc5w] [qLgbEgFwoqchYFAGqMocshvKENOJjhaFOdhStt8phLcfJIyTpryiW8heA-I-zC5J3-Ky483GgA88F1G8CfVgUfMfYKU62ivg0w12sBTI_uURtEAjNA] Your browser does not support the video tag. Your browser does not support the video tag. 26B & 31B Unprecedented intelligence-per-parameter Frontier intelligence on personal computers Learn more [241kUbfd5jozU-ETxthrBSW7_xgCEvMzxVVuThwIzazfHluocz1svdDFjkXpZjNqbGEwMCJDtwa9u9QJAjgOfa5Y8-ss43U4yClrEY241305bqThgbU] [LoBNGAVAJpiKOwh-79dLSX_swo_0DOrHKQ4pxZ_TaD5NzTtTIsaQ6wnglBvW8gvyPVd1tMLPVeqKtbVW8z-n3_3SDy_e3A9DZwFvBvDhgxl40OPDTg] Your browser does not support the video tag. Your browser does not support the video tag. E2B & E4B Maximum compute and memory efficiency A new level of intelligence for mobile and IoT devices Learn more [c9w8JGekqO0jTMuXmWjsS9bZJVlNKAl1F5rJmg-emLQkQul5PNmENZosqnmp7kmRWTz0XsmIFK1BVob56zvgb9fw_9NmX4yDCDMrJ442CB9bKNRc5w] [qLgbEgFwoqchYFAGqMocshvKENOJjhaFOdhStt8phLcfJIyTpryiW8heA-I-zC5J3-Ky483GgA88F1G8CfVgUfMfYKU62ivg0w12sBTI_uURtEAjNA] Your browser does not support the video tag. Your browser does not support the video tag. 26B & 31B Unprecedented intelligence-per-parameter Frontier intelligence on personal computers Learn more * Capabilities * Performance * Safety * Download Capabilities Slide 1 of 5 Agentic workflows Build autonomous agents that plan, navigate apps, and complete tasks on your behalf, with native support for function calling. Multimodal reasoning Develop applications with strong audio and visual understanding, for rich multimodal support. Support for 140 languages Create multilingual experiences that go beyond translation and understand cultural context. Fine tuning Improve performance for specific tasks by training Gemma using your preferred frameworks and techniques. Efficient architecture Run models on your own hardware for efficient development and deployment. --------------------------------------------------------------------- Performance Industry-leading efficiency View model card [gemma__gem][gemma__gem] Gemma Gemma Gemma Gemma Gemma Benchmark 4 31B IT 4 26B A4B 4 E4B IT 4 E2B IT 3 27B Thinking IT Thinking Thinking IT Thinking Arena AI (text) 1452 1441 -- -- 1365 As of 4/2/26 MMMLU No 85.2% 82.6% 69.4% 60.0% 67.6% Multilingual Q&A tools MMMU Pro Multimodal 76.9% 73.8% 52.6% 44.2% 49.7% reasoning AIME 2026 No 89.2% 88.3% 42.5% 37.5% 20.8% Mathematics tools LiveCodeBench v6 Competitive 80.0% 77.1% 52.0% 44.0% 29.1% coding problems GPQA Diamond No Scientific tools 84.3% 82.3% 58.6% 43.4% 42.4% knowledge t2-bench Agentic Retail 86.4% 85.5% 57.5% 29.4% 6.6% tool use These models were evaluated against a large collection of datasets and metrics to cover different aspects of text generation. See additional benchmarks in model card. --------------------------------------------------------------------- E2B and E4B A new level of intelligence for mobile and IoT devices Audio and vision support for real-time edge processing. They can run completely offline with near-zero latency on edge devices like phones, Raspberry Pi, and Jetson Nano. Try in Google AI Edge Gallery --------------------------------------------------------------------- 26B and 31B Frontier intelligence, efficient performance Advanced reasoning for IDEs, coding assistants, and agentic workflows. These models are optimized for consumer GPUs -- giving students, researchers, and developers the ability to turn workstations into local-first AI servers. Try in Google AI Studio --------------------------------------------------------------------- Safety Gemma 4 models undergo the same rigorous infrastructure security protocols as our proprietary models. By choosing Gemma 4, enterprises and sovereign organizations gain a trusted, transparent foundation that delivers state-of-the-art capabilities while meeting the highest standards for security and reliability. Learn more --------------------------------------------------------------------- Download Model weights [gemma-ecos] [gemma-ecos] Hugging Face [gemma-ecos] [gemma-ecos] Ollama [gemma-ecos] [gemma-ecos] Kaggle [gemma-ecos] [gemma-ecos] LM Studio [ecosystem_] [ecosystem_] Docker --------------------------------------------------------------------- Run Train and deploy [jax_y6ruUH] [jax_y6ruUH] Jax [try__verte] [try__verte] Vertex AI [gemma-ecos] [gemma-ecos] Keras [gemma-ecos] [gemma-ecos] Google AI Edge [gemma-ecos] [gemma-ecos] Google Kubernetes Engine [gemma-ecos] [gemma-ecos] Ollama [F75RQDkVmDPzXVe53VodHM1u78XnXQJujfUf6lQNjkNlCTjZLYZ2hPD3-p2i4khXLWUGzcGqCfDW0ZgloF_3CXm62jpeNK8bMj8QhQcVec1ZZls] [ybH3Uxy0dhfm1_7uBBQJVLdD9FEYNScrQISKF5QS_oUsgGaOA8ZyXuOsuFxYp0D9QIfrP4BzCM0Fh1RuqjUUeChGRQWdjEvAblrgBBWDNyaAKXxH] Join the Gemmaverse Explore how others build with Gemma Learn more Follow us Sign up for updates on our latest innovations I accept Google's Terms and Conditions and acknowledge that my information will be used in accordance with Google's Privacy Policy. [ ] Sign up Build AI responsibly to benefit humanity Models Gemini Nano Banana Gemini Audio footer_gemma__light footer_gemma__dark Gemma Genie Lyria Veo Research Evals Breakthroughs Publications Responsibility Science AlphaFold AlphaGenome WeatherNext AlphaEarth Products Gemini app Google AI Studio Google Antigravity Learn more About News Careers National Partnerships for AI The Podcast About Google Google products Privacy Terms Cookies management controls