NVIDIA Groq 3 LPX in Full Production, Delivers Record Inference Speed for Agentic AI Workloads

NVIDIA Groq 3 LPX accelerates AI inference with high-speed token generation for agentic systems, enhancing performance in cloud applications.

Quiver AI Summary

NVIDIA has announced the full production launch of the Groq 3 LPX, an interactive AI inference accelerator designed to enhance performance for agentic coding and other latency-sensitive applications. This new product improves token generation rates significantly, achieving a record of 3,400 output tokens per second in benchmark testing with the Gemma 4 31B model. Groq 3 LPX is built to extend the capabilities of the NVIDIA Vera Rubin NVL72 systems, providing a fast and versatile platform for AI factories, which allows agents to perform tasks such as coding much more quickly. Nebius, a pioneering AI cloud provider, will be the first to incorporate Groq 3 LPX into its inference platform, facilitating ultra-responsive AI applications for developers. NVIDIA's advancements aim to push the boundaries of AI inference, improving throughput and efficiency across the industry.

Potential Positives

NVIDIA Groq 3 LPX is now in full production, enhancing the inferred performance of AI systems with record-breaking token generation rates.
Achieved a benchmark record of 3,400 output tokens per second, the fastest performance for the Gemma 4 31B model, significantly benefiting agentic AI applications.
Nebius has become the first AI cloud to adopt Groq 3 LPX, expanding access to advanced AI inference capabilities for developers and enterprises.

Potential Negatives

The press release highlights intense competition in the AI inference market, particularly with the introduction of NVIDIA Groq 3 LPX, which may overshadow existing products from other companies.
It references various risks and uncertainties associated with NVIDIA's forward-looking statements, potentially undermining investor confidence.
The company discloses reliance on third parties for manufacturing, which can introduce vulnerabilities in supply chain management and product availability.

FAQ

What is NVIDIA Groq 3 LPX?

NVIDIA Groq 3 LPX is an interactive AI inference accelerator designed to enhance token generation rates for agentic systems.

How does Groq 3 LPX improve AI inference?

It dramatically increases token generation speeds, improving responsiveness for latency-sensitive workloads and agentic tasks.

Who is the first to adopt Groq 3 LPX?

Nebius is the first AI cloud platform to adopt NVIDIA Groq 3 LPX for its Token Factory production.

What performance benchmarks has Groq 3 LPX achieved?

It achieved a record output of 3,400 tokens per second in AI benchmarking, the fastest ever for the Gemma 4 31B model.

How does Groq 3 LPX benefit developers?

It allows developers to access ultra-fast token generation speed, improving the performance of responsive agentic AI applications.

Disclaimer: This is an AI-generated summary of a press release distributed by GlobeNewswire. The model used to summarize this release may make mistakes. See the full release here.

$NVDA Insider Trading Activity

$NVDA insiders have traded $NVDA stock on the open market 45 times in the past 6 months. Of those trades, 0 have been purchases and 45 have been sales.

Here’s a breakdown of recent trading of $NVDA stock by insiders over the last 6 months:

MARK A STEVENS has made 0 purchases and 7 sales selling 2,106,682 shares for an estimated $445,605,062.
AJAY K PURI (EVP, Worldwide Field Ops) has made 0 purchases and 5 sales selling 600,000 shares for an estimated $109,432,183.
COLETTE KRESS (EVP & Chief Financial Officer) has made 0 purchases and 21 sales selling 62,650 shares for an estimated $10,956,705.
AARTI S. SHAH has made 0 purchases and 3 sales selling 19,000 shares for an estimated $3,357,549.
STEPHEN C NEAL sold 15,500 shares for an estimated $3,343,863
DONALD F JR ROBERTSON (Principal Accounting Officer) has made 0 purchases and 6 sales selling 5,396 shares for an estimated $942,944.
JOHN DABIRI has made 0 purchases and 2 sales selling 3,629 shares for an estimated $689,189.

To track insider transactions, check out Quiver Quantitative's insider trading dashboard. You can access data on insider stock transactions through the Quiver Quantitative API insider transaction endpoint.

$NVDA Revenue

$NVDA had revenues of $81.6B in Q1 2027. This is an increase of 85.23% from the same period in the prior year.

You can track NVDA financials on Quiver Quantitative's NVDA stock page.

You can access data on NVDA stock through the Quiver Quantitative API.

$NVDA Congressional Stock Trading

Members of Congress have traded $NVDA stock 23 times in the past 6 months. Of those trades, 9 have been purchases and 14 have been sales.

Here’s a breakdown of recent trading of $NVDA stock by members of Congress over the last 6 months:

REPRESENTATIVE SAM LICCARDO sold up to $50,000 on 07/21.
REPRESENTATIVE DAN NEWHOUSE sold up to $15,000 on 07/10.
SENATOR SHELDON WHITEHOUSE has traded it 3 times. They made 0 purchases and 3 sales worth up to $550,000 on 06/30, 05/08.
REPRESENTATIVE CLEO FIELDS has traded it 3 times. They made 3 purchases worth up to $45,000 on 06/26 and 0 sales.
REPRESENTATIVE MICHAEL A. RULLI purchased up to $15,000 on 06/25.
REPRESENTATIVE MATTHEW VAN EPPS sold up to $15,000 on 06/16.
REPRESENTATIVE DANIEL MEUSER has traded it 4 times. They made 0 purchases and 4 sales worth up to $60,000 on 05/27, 04/24, 03/25, 02/25.
REPRESENTATIVE JOHN MCGUIRE purchased up to $15,000 on 04/15.
REPRESENTATIVE GILBERT RAY CISNEROS, JR. has traded it 3 times. They made 1 purchase worth up to $15,000 on 03/13 and 2 sales worth up to $30,000 on 04/14, 03/25.
REPRESENTATIVE LIZZIE FLETCHER sold up to $15,000 on 04/08.
SENATOR ALAN ARMSTRONG has traded it 2 times. They made 2 purchases worth up to $115,000 on 03/30, 03/27 and 0 sales.
REPRESENTATIVE TIM MOORE sold up to $50,000 on 03/24.
SENATOR JOHN BOOZMAN purchased up to $15,000 on 03/19.

To track congressional stock trading, check out Quiver Quantitative's congressional trading dashboard. You can access data on congressional stock trades through the Quiver Quantitative API Congress trades endpoint.

$NVDA Hedge Fund Activity

We have seen 3,227 institutional investors add shares of $NVDA stock to their portfolio, and 2,556 decrease their positions in their most recent quarter.

Here are some of the largest recent moves:

CALIFORNIA STATE TEACHERS RETIREMENT SYSTEM added 6,970,761,172 shares (+18999.7%) to their portfolio in Q2 2026, for an estimated $1,394,779,602,905
JPMORGAN CHASE & CO added 449,404,578 shares (+inf%) to their portfolio in Q2 2026, for an estimated $89,921,362,012
INVESCO LTD. added 186,832,782 shares (+130.9%) to their portfolio in Q2 2026, for an estimated $37,383,371,350
SIXTH STREET PARTNERS MANAGEMENT COMPANY, L.P. added 160,214,733 shares (+inf%) to their portfolio in Q2 2026, for an estimated $32,057,365,925
SG AMERICAS SECURITIES, LLC added 62,298,007 shares (+inf%) to their portfolio in Q2 2026, for an estimated $12,465,208,220
FMR LLC added 32,198,580 shares (+3.2%) to their portfolio in Q2 2026, for an estimated $6,442,613,872
CALIFORNIA PUBLIC EMPLOYEES RETIREMENT SYSTEM removed 22,264,066 shares (-32.6%) from their portfolio in Q2 2026, for an estimated $4,454,816,965

To track hedge funds' stock portfolios, check out Quiver Quantitative's institutional holdings dashboard. You can access data on hedge funds moves and 13F filings through the Quiver Quantitative API 13F endpoint.

$NVDA Analyst Ratings

Wall Street analysts have issued reports on $NVDA in the last several months. We have seen 2 firms issue buy ratings on the stock, and 0 firms issue sell ratings.

Here are some recent analyst ratings:

Needham issued a "Buy" rating on 05/21/2026
Benchmark issued a "Buy" rating on 03/31/2026

To track analyst ratings and price targets for $NVDA, check out Quiver Quantitative's $NVDA forecast page.

$NVDA Price Targets

Multiple analysts have issued price targets for $NVDA recently. We have seen 26 analysts offer price targets for $NVDA in the last 6 months, with a median target of $308.5.

Here are some recent targets:

Jack Zhou from China Renaissance set a target price of $319.0 on 06/05/2026
N. Quinn Bolton from Needham set a target price of $270.0 on 06/02/2026
Gil Luria from DA Davidson set a target price of $300.0 on 06/01/2026
Ivan Feinseth from Tigress Financial set a target price of $425.0 on 05/27/2026
Srini Pajjuri from RBC Capital set a target price of $270.0 on 05/21/2026
Timothy Arcuri from UBS set a target price of $280.0 on 05/21/2026
William Stein from Truist Securities set a target price of $307.0 on 05/21/2026

Full Release

News Summary:

In Artificial Analysis benchmarking, Groq 3 LPX showcased world-class speed for agentic coding and other latency-sensitive workloads.
NVIDIA Groq 3 LPX extends the inference performance of NVIDIA Vera Rubin NVL72 systems by dramatically increasing token generation rates.
Nebius is the first AI cloud to adopt NVIDIA Groq 3 LPX.

PALO ALTO, Calif., Aug. 24, 2026 (GLOBE NEWSWIRE) -- Hot Chips— NVIDIA today announced that NVIDIA Groq 3 LPX , the interactive AI inference accelerator, is now in full production. An extension of the NVIDIA Vera Rubin platform, Groq 3 LPX delivers a major boost in AI inference by enabling ultrafast token generation for highly responsive agentic systems.

Agentic systems can generate massive volumes of tokens across hundreds or thousands of inference steps, making faster token generation critical for agents to reason, act and complete complex tasks in real time.

Vera Rubin NVL72 systems provide the most versatile training and inference platform for every AI factory. NVIDIA Groq 3 LPX extends the inference performance of Vera Rubin NVL72 by dramatically increasing the rate of token generation, providing premium user experiences for context-heavy workloads so agents can act at extreme speeds.

NVIDIA Groq 3 LPX is pushing the frontier of AI inference. It delivered a record 3,400 output tokens per second in Artificial Analysis benchmarking running Gemma 4 31B, an open source agentic model, with a 100,000-token context critical for agentic systems — the fastest performance ever recorded for the model.

Groq 3 LPX enables agentic tasks such as coding in minutes versus hours, providing 4x faster responsiveness for agents and latency-sensitive workloads than the nearest alternative platform.

“Inference is the growth engine of AI. NVIDIA Grace Blackwell and NVL72 revolutionized large language model inference with an unprecedented leap in performance and efficiency,” said Jensen Huang, founder and CEO of NVIDIA. “Vera Rubin extends that vision with workload-optimized AI factory configurations designed for the era of agentic AI, advancing the performance frontier with LPX for ultrafast token generation. This transforms how intelligence is produced, delivering another giant leap in AI throughput, efficiency and responsiveness, just as demand for AI computation is accelerating worldwide.”

Groq 3 LPX — The Interactive AI Inference Accelerator
Agentic AI creates two distinct computing challenges: efficiently processing enormous amounts of context and generating tokens with extremely low latency.

NVIDIA Groq 3 LPX is purpose-built to extend Vera Rubin’s interactivity — the rate at which tokens are generated for an individual user, determining how quickly an agent can complete each step of its work.

Faster generation gives agents more time to inspect files, write and test code, call tools, verify results and iterate while maintaining a responsive user experience.

AI Cloud Momentum for Groq 3 LPX
AI clouds are becoming the engines of the AI economy, giving enterprises and developers access to advanced infrastructure for training, reasoning and inference at scale. For providers serving latency-sensitive, high-volume inference workloads, NVIDIA Groq 3 LPX provides a path to deploy differentiated compute in proven rack-scale systems.

Nebius, a leading AI cloud, plans to bring NVIDIA Groq 3 LPX to Nebius Token Factory , its production inference platform, giving developers access to extreme token generation speed for highly responsive agentic AI applications.

“Generation is the phase of inference that determines how responsive an AI system actually is, and that’s exactly what NVIDIA Groq 3 LPX is built to accelerate,” said Danila Shtan, chief technology officer of Nebius. “As the first AI cloud bringing it to production via Nebius Token Factory, we’re making sure every step of an agent’s loop feels instant — through the same API developers are already using, with no migration to a new stack.”

Following Nebius, purpose-built AI inference cloud Groq plans to be among the platform’s earliest adopters.

Extreme Codesign for AI Factories
Through extreme codesign across seven chips and five purpose-built racks, NVIDIA Vera Rubin is the most extensive AI factory platform.

NVIDIA Vera Rubin NVL72 and Groq 3 LPX tackle the various workload requirements of customer AI factories, including frontier model makers and open model service providers.

These rack platforms feature NVIDIA BlueField®-4 DPUs and work in combination with NVIDIA Vera CPU racks, NVIDIA Vera BlueField-4 STX storage and NVIDIA Spectrum™-6 SPX Ethernet to optimize multi-agent systems for the highest throughput per watt and the lowest-latency inference.

About NVIDIA
NVIDIA (NASDAQ: NVDA) is the world leader in AI and accelerated computing.

For further information, contact:
Alex Shapiro
Corporate Communications
NVIDIA Corporation
[email protected]

Certain statements in this press release including, but not limited to, statements as to: expectations with respect to growth, performance, availability, and benefits of NVIDIA’s products, services and technologies, and related trends and drivers; expectations with respect to NVIDIA’s third party arrangements, including with its collaborators and partners; expectations with respect to technology developments, and related trends and drivers; projected market growth and trends; expectations with respect to AI and related industries; and other statements that are not historical facts are forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended, which are subject to the “safe harbor” created by those sections based on management’s beliefs and assumptions and on information currently available to management and are subject to risks and uncertainties that could cause results to be materially different than expectations. Important factors that could cause actual results to differ materially include: global economic and political conditions; NVIDIA’s reliance on third parties to manufacture, assemble, package and test NVIDIA’s products; the impact of technological development and competition; development of new products and technologies or enhancements to NVIDIA’s existing products and technologies; market acceptance of NVIDIA’s products or NVIDIA’s partners’ products; design, manufacturing or software defects; changes in consumer preferences or demands; changes in industry standards and interfaces; unexpected loss of performance of NVIDIA’s products or technologies when integrated into systems; NVIDIA’s ability to realize the potential benefits of business investments or acquisitions; and changes in applicable laws and regulations, as well as other factors detailed from time to time in the most recent reports NVIDIA files with the Securities and Exchange Commission, or SEC, including, but not limited to, its Annual Report on Form 10-K and Quarterly Reports on Form 10-Q. Copies of reports filed with the SEC are posted on NVIDIA’s website and are available from NVIDIA without charge. These forward-looking statements are not guarantees of future performance and speak only as of the date hereof, and, except as required by law, NVIDIA disclaims any obligation to update these forward-looking statements to reflect future events or circumstances.

Many of the products and features described herein remain in various stages and will be offered on a when-and-if-available basis. The statements above are not intended to be, and should not be interpreted as a commitment, promise or legal obligation, and the development, release and timing of any features or functionalities described for our products is subject to change and remains at the sole discretion of NVIDIA. NVIDIA will have no liability for failure to deliver or delay in the delivery of any of the products, features or functions set forth herein.

© 2026 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, BlueField and NVIDIA Spectrum are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Groq and LPU are used under license from Groq, Inc. Other company and product names may be trademarks of the respective companies with which they are associated. Features, pricing, availability and specifications are subject to change without notice.

A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/f9f9a4ac-5592-4829-b98f-898c29c59625