News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
Google Tensor G5

Google Tensor G5

Custom mobile processor for Pixel 10 phones

Google designed the Tensor G5 system on a chip for its Pixel 10 smartphone series. Built on a 3 nm process by TSMC, it focuses on on-device artificial intelligence and camera processing rather than raw benchmark scores.

Share on WhatsApp

  • Manufactured by TSMC on a 3 nm process node
  • Runs Gemini Nano generative AI model on device
  • Features a new image signal processor for cameras
  • Succeeds the Samsung-made Google Tensor G4
  • Powers the Pixel 10 series of smartphones

What it is

The Google Tensor G5 is a custom system on a chip designed by Google for its Pixel 10 series of smartphones. It represents the fifth generation of Google’s proprietary silicon. The company states this iteration delivers significant improvements in performance and efficiency compared to its predecessor. Manufactured using a 3 nanometre process node by TSMC, the chip integrates specialized hardware for artificial intelligence tasks and image processing. Its primary role is to enable advanced on-device features, such as generative AI models and enhanced camera capabilities, while maintaining battery life throughout a day of use.

How it came about

Google introduced its first Tensor chip in 2021 with a focus on machine learning rather than raw speed. The company stated it was comfortable not leading in benchmark tests if the user experience improved. For the G5 generation, Google shifted manufacturing from Samsung to TSMC. This move allowed Google to build what it describes as its first truly custom chip, moving away from relying on Exynos roots. The design process involved close collaboration with Google Research and DeepMind teams to integrate the latest AI innovations directly into the silicon architecture for the Pixel 10 launch in 2025.

Inside the chip

The Tensor G5 architecture prioritises artificial intelligence and media processing. It includes a tensor processing unit that Google claims is up to sixty percent more powerful than the previous generation. This unit runs the Gemini Nano generative AI model locally on the device. The chip also features a new image signal processor. This component handles video and photo tasks, supporting ten-bit video recording and motion deblur. Security hardware is integrated to protect data from manufacturing through daily use. The design aims to run AI features efficiently, with Google stating the new model runs faster and uses less power than before.

How it was made

TSMC manufactures the Tensor G5 using its three nanometre process node. This advanced lithography technique allows for a higher density of transistors within the same physical area. Google states this results in a chip that is both more powerful and more energy efficient than prior generations made by Samsung. The shift to TSMC is noted as a key step in creating a fully custom design. The manufacturing process includes embedded security measures to ensure the integrity of the hardware before it reaches consumers. No specific transistor count or package type is disclosed in the available information.

Where it went

The Tensor G5 powers the Pixel 10, Pixel 10 Pro, and Pixel 10 Pro XL smartphones. It enables features such as Magic Cue for proactive assistance and Scam Detection. The chip drives the camera system, allowing for one hundred times zoom and improved low light performance. It supports on-device generative AI tasks like voice editing in Gboard and summarisation in Recorder. The security components work with the Titan M2 chip to create content credentials for images. These uses highlight the chip’s role in delivering smart, helpful features rather than just raw computational speed for gaming or heavy multitasking.

Versions and family

The Tensor G5 serves as the sole processor for the entire Pixel 10 phone series. It succeeds the Google Tensor G4, which was used in the previous generation of devices. Google describes the G5 as the biggest upgrade to its custom silicon since the programme began. There are no distinct variants of the G5 chip mentioned for different phone models within the Pixel 10 lineup. The successor to this chip has not been announced. The predecessor, Tensor G4, was manufactured by Samsung, marking a clear transition in supply chain and design philosophy for Google.

Why it matters

The release of Tensor G5 marks Google’s full transition to TSMC for its flagship mobile chips. Industry observers note that while the chip fixes overheating issues seen in earlier generations, it still trails competitors in raw benchmark performance. Google maintains that its strategy focuses on user experience and AI capabilities over synthetic scores. The chip enables a seven year software update policy for Pixel devices. Its integration of generative AI sets a precedent for on-device processing in smartphones. Critics argue the performance gap with rivals like Qualcomm remains a concern for long term value.

Problems and reception

Reviews indicate that the Tensor G5 runs cooler than its predecessors, addressing past thermal complaints. However, benchmarks show it remains significantly slower than competing flagships like the Snapdragon 8 Elite. Some reviewers describe the performance gap as a potential red flag, despite the improved user experience. The chip receives praise for enabling unique AI features and maintaining strong battery life. Concerns exist regarding the high price of Pixel phones relative to the chipset’s raw power. Overall, the reception highlights a trade off between specialised AI utility and traditional computational horsepower.

Questions people ask about Google Tensor G5

Who manufactures the Google Tensor G5?

The Google Tensor G5 is manufactured by TSMC using their three nanometre process node. This marks a change from previous generations, which were produced by Samsung. The shift to TSMC allows for greater efficiency and performance density in the custom designed chip.

What is the main purpose of the Tensor G5 chip?

The primary purpose of the Tensor G5 is to enable advanced on-device artificial intelligence and improve camera processing. It is designed to run generative AI models like Gemini Nano efficiently. Google prioritises these smart features over winning raw performance benchmarks against other mobile processors.

How does Tensor G5 compare to its predecessor?

Google states the Tensor G5 offers a major performance boost over the Tensor G4. It features a tensor processing unit that is up to sixty percent more powerful. The new chip also runs cooler and is more energy efficient, thanks to the move to a three nanometre manufacturing process.

Which phones use the Google Tensor G5?

The Google Tensor G5 is used exclusively in the Pixel 10 series of smartphones. This includes the standard Pixel 10, the Pixel 10 Pro, and the Pixel 10 Pro XL. The chip powers all the core functions and AI features of these devices.

Good reading and sources

    Where this page comes from

    There is no English Wikipedia article on Google Tensor G5 yet, so the facts on this page come from the sources listed above: blog.google/products-and-platforms/devices/pixel/tensor-g5-pixel-10/, 9to5google.com/2025/08/31/google-pixel-10-tensor-g5/. Some are the subject's own pages, so its claims about itself are reported as its claims. EveryChip wrote the text in its own words, with AI assistance, and compares it with the sources to make sure no passage is copied.

    It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

    Photo credits on this page

    The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

    • Apple M1: Henriok, CC0, source
    • Sycamore: Google ( https://www.youtube.com/channel/UCK8sQmJBp8GCxrOtXWBpyEA ), CC BY 3.0, source

    The weekly digest

    Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.