Skip to content
Trending storyDeveloping

Liquid AI reports over 21,000 output tokens/s on an NVIDIA B300

1 article1 sourcesince Oct 13Last article 1h ago ·

Overview

AISummary of 1 article

Liquid AI says its model reaches more than 21,000 output tokens per second at high concurrency on an NVIDIA B300 GPU. The claim appears in the third post of a thread on X from the company's account.

The post names no model and gives no further benchmark details, such as batch size, sequence lengths or precision.

Written by AI from the articles below · updated Oct 13, 1:22 PM ET

Check the sources:

Latest developmentOct 13, 1:11 PM ET
Liquid AI reports over 21k output tokens/s on Nvidia B300 GPU

Article timeline

The articles in this story. Times are ET.

Oct 13
  1. Liquid AIOfficial
    Liquid AI reports over 21k output tokens/s on Nvidia B300 GPU

    AILiquid AI says its model reaches more than 21,000 output tokens per second at high concurrency on an Nvidia B300 GPU. The post is the third in a thread, and the source gives no model name or further details.

    Image from @liquidai's post

Heat trend

Not enough continuous observations to show a trend yet.