Google releases two self-developed AI chips, 8tx and 8i Max, with up to twice the speed
Google has released two self-developed AI chips redesigned based on TPU, 8tx and 8i Max, respectively targeting high data security requirements and high-intensity AI computing scenarios. 8tx combines Google's self-developed technology with AMD processors, supports hardware-level data encryption, and boosts processing speed to up to twice that of the previous generation with almost no performance loss due to encryption; 8i Max integrates two chips in the same package to provide larger memory and stronger computing power, suitable for AI coding assistants, complex mathematical reasoning, and drug development. After the announcement, Alphabet's stock rose more than 3% in early trading.
Why read this
AI score 75
The original text explains the positioning differences and speedup margins of the two TPUs, which can be used to judge Google's approach to segmenting specialized computing power.
Topics
Body · AI translation
Google Releases Two AI Chips: Up to Twice the Speed, Challenging Nvidia Phoenix Tech Download the App for Exclusive Early Access November 10, 2026 07:16:32 From Beijing Updated November 10, 2026 07:21:44
Phoenix Tech News, November 10 (Beijing Time) — According to Reuters, Google announced on Monday the launch of two new self-developed AI chips, aimed respectively at data security and high-intensity AI computing needs, further challenging Nvidia's dominance in the AI chip market. After the announcement, shares of Google's parent company Alphabet rose more than 3% in early trading on Monday.
The two chips released this time are named 8tx and 8i Max. Both are redesigned based on Google's existing Tensor Processing Units (TPUs) and optimized for the needs of different enterprise customers.
Among them, 8tx is mainly aimed at government agencies and regulated industries such as finance and healthcare that have high data security requirements. The chip combines Google's self-developed technology with AMD processors and supports hardware-level data encryption, so that sensitive information can remain protected during processing.
Google said that compared with the previous generation, 8tx can deliver up to twice the processing speed, while incurring almost no performance loss from data encryption. This means enterprises can balance computing efficiency and information security when handling sensitive data.
The other chip, 8i Max, is mainly aimed at AI applications that need to process massive amounts of information. Google integrates two chips into the same package to provide greater memory capacity and stronger computing power.
According to Google, 8i Max is especially suitable for tasks such as AI coding assistants, complex mathematical reasoning, and drug development. Such applications often require AI models to process large amounts of code, research data, or complex computational processes at the same time, placing higher demands on chip memory and computing power.
For a long time, Google's TPUs have mainly been used to support internal products such as Search, YouTube, and Gemini. In recent years, Google has gradually opened TPU computing power to external enterprises through its cloud business, hoping to attract more AI enterprise customers and reduce its dependence on Nvidia GPUs.
This strategy has already begun to affect Google's performance. Alphabet previously said that TPU sales made an important contribution to third-quarter results. Driven by continuously growing AI demand, Google Cloud's third-quarter revenue more than doubled year over year to $30.71 billion.
At present, Nvidia still holds a dominant position in the AI chip market, but as enterprises' needs for AI training, inference, and data security continue to diversify, Google is trying to expand its competitiveness in the AI computing market by designing dedicated chips for specific application scenarios. (Editor/Yu Lei)
For more first-hand news, please download the Phoenix News app and subscribe to Phoenix Tech. For in-depth reports, please search "Phoenix Tech" on WeChat.