Google Fires Back At Nvidia With Its New Ironwood AI Chip

Author: Anusuya Lahiri | November 07, 2025 06:14am

Google, owned by Alphabet Inc. (NASDAQ:GOOG) (NASDAQ:GOOGL), introduced a new generation of artificial intelligence–focused computing hardware as demand accelerates for advanced AI workloads.

The company rolled out Ironwood, its seventh-generation Tensor Processing Unit (TPU), alongside new Arm-based Axion processors.

Both platforms are engineered to deliver higher performance, lower costs, and improved energy efficiency for large-scale AI applications.

Also Read: Google Stock Is Up 70%, But One Analyst Says The AI Rally Is Just Beginning

Ironwood Targets Large-Scale AI Training And Inference

Ironwood, which will be generally available in the coming weeks, is designed for the most demanding AI and machine-learning workloads—from large-scale training to real-time inference.

Google said Ironwood delivers up to 10 times the peak performance of the TPU v5p and more than four times the performance per chip compared with the previous generation.

Anthropic, one of Google's key AI partners, plans to deploy up to one million TPUs to train and serve its Claude models, citing Ironwood's gains in speed and scalability.

Axion CPU Line Expands To N4A And C4A

Google also broadened its Axion CPU lineup, unveiling the N4A virtual machine and C4A metal instance, both based on custom Arm architecture.

The company claims N4A offers up to twice the price-performance of comparable x86-based machines, while C4A metal provides dedicated physical servers for specialized workloads such as automotive systems and large-scale simulations.

Positioning Against Cloud And AI Rivals

The new hardware underscores Google's push to compete more aggressively with Microsoft Corp. (NASDAQ:MSFT), Amazon.com Inc. (NASDAQ:AMZN), and Meta Platforms Inc. (NASDAQ:META) for AI infrastructure leadership.

While Nvidia Corp. (NASDAQ:NVDA) Graphics Processing Units still underpin most AI models, Google is betting that its TPUs' cost and performance advantages will draw developers, CNBC reported.

Cloud Growth And Rising Capex

To support expanding AI infrastructure needs, Google is introducing cloud upgrades and increasing capital spending to an expected $93 billion this year from $85 billion.

CEO Sundar Pichai said AI-driven products—including TPU- and GPU-based solutions—remain a major growth engine for Google Cloud, which posted 34% year-over-year revenue growth in the third quarter to $15.15 billion.

Price Action: GOOG stock was trading lower by 0.35% to $284.34 premarket at last check Friday.

Read Next:

• Meta Bets Big On AI: Ad Revenue Set To Outpace Google

Photo by Markus Mainka via Shutterstock

Posted In: AMZN GOOG GOOGL META MSFT NVDA