GBAF Logo
Global Banking & Finance Awards® 2026 Nominations open, free to enter Nominate now →
Google to introduce two variants of in-house chips, Bloomberg News reports - Finance news and analysis from Global Banking & Finance Review
Finance

Google to introduce two variants of in-house chips, Bloomberg News reports

Published by Global Banking & Finance Review

Posted on November 9, 2026

2 min read

· Last updated: November 9, 2026

Add as preferred source on Google

Google Unveils Two New In-House AI Chips to Compete with Nvidia

Google's Latest AI Chip Innovations and Market Impact

Introduction of New Tensor Processing Units

Nov 9 (Reuters) - Alphabet's Google is introducing two new variations of its in-house tensor processing units, Bloomberg News reported on Monday.

Market Reaction and Stock Performance

The search giant's shares were up more than 2% in premarket trading. Through last close, the stock has fallen 9% so far this year.

Company Response and Report Verification

Alphabet did not immediately respond to a Reuters request for comment. Reuters could not independently verify the report.

Competition with Nvidia in AI Workloads

Google's homegrown chips, once reserved for internal use, have emerged as a challenger to Nvidia's pricey graphics processors that dominate AI workloads worldwide.

Details on TPU 8tx and 8i Max Variants

The TPU 8tx and 8i Max variants are not new chips, but reconfigured versions designed to handle workloads customers have been asking for, Google's chief technologist for AI infrastructure Amin Vahdat told Bloomberg News.

TPU 8tx: Secure and Confidential Workloads

The 8tx is designed for secure and confidential workloads used by government agencies and companies in regulated industries, while the 8i Max is designed for AI applications that require long context windows, the report said.

TPU 8i Max: Long Context Window AI Applications

(Reporting by Anhata Rooprai in Bengaluru; Editing by Jonathan Ananda)

Key Takeaways

  • TPU 8tx is tailored for secure, confidential workloads used by government and regulated industries, addressing demand for privacy‑focused AI compute (siliconreport.com).
  • TPU 8i Max, optimized for long‑context AI applications, reflects Google’s focus on reasoning and inference‑heavy workloads with specialized hardware architecture (venturebeat.com).
  • Google’s separation of training and inference into TPU 8 variants highlights its strategic shift toward vertically integrated, workload‑specific silicon design, aiding competitiveness with Nvidia and reinforcing its AI‑infrastructure ambitions (siliconreport.com).

References

Frequently Asked Questions

What are the new chip variants Google is introducing?
Google is introducing two variants of its tensor processing units: the TPU 8tx and 8i Max, which are updated versions designed for specific customer needs.
Why are Google’s new TPUs significant?
Google's TPUs are significant because they offer alternatives to Nvidia's dominant AI chips, catering to secure, confidential applications and AI workloads needing long context windows.
How did Alphabet's stock react to the news?
Alphabet's shares rose over 2% in premarket trading after news of the new chip variants, despite having dropped 9% so far this year.
Who are the target users for the Google TPU 8tx variant?
The TPU 8tx is targeted at government agencies and companies in regulated industries requiring secure and confidential workload processing.
What is the focus of the TPU 8i Max variant?
The TPU 8i Max variant is designed for AI applications that require handling long context windows.

Tags

Related Articles

More from Finance

Explore more articles in the Finance category