Clarifai breaks 400 TOKENS PER SECOND on KIMI K2.5 - GTC KEYNOTE

Clarifai
44,855 views March 17, 2026

Clarifai gets featured in Jensen Huang's keynote at NVIDIA's annual GTC conference as the first inference provider to break 400 tokens per second on Moonshot AI's Kimi K2. Signup to try the fastest GPU inference in the world for free: https://clarifai.com/signup?utm_source=YouTube&utm_medium=video&utm_campaign=clarifai_youtube_description Learn more at: https://clarifai.com?utm_source=YouTube&utm_medium=video&utm_campaign=clarifai_youtube_description

Keyboard shortcuts

On. Switch them off if they collide with your assistive tools; ? still opens this sheet.

Go to

Press g then the letter.

  • gh Latest
  • gs Sources
  • gm Media
  • gv Videos
  • gp Podcasts
  • gc Calendar
  • gd Decoder
  • gz Dataviz
  • ga Datasets
  • gb Blog
  • gk Markets
  • gj Careers
  • gn Prompt Notebook

On this page

  • / Focus search, where there is one
  • t Back to top
  • ? This list
  • Esc Close