Tech

SambaNova hits 198 tokens per second on the full, non-distilled DeepSeek-R1 671B with only 16 SN40L RDU chips

Share
Share

  • SambaNova runs DeepSeek-R1 at 198 tokens/sec using 16 custom chips
  • The SN40L RDU chip is reportedly 3X faster, 5X more efficient than GPUs
  • 5X speed boost is promised soon, with 100X capacity by year-end on cloud

Chinese AI upstart DeepSeek has very quickly made a name for itself in 2025, with its R1 large-scale open source language model, built for advanced reasoning tasks, showing performance on par with the industry’s top models, while being more cost-efficient.

SambaNova Systems, an AI startup founded in 2017 by experts from Sun/Oracle and Stanford University, has now announced what it claims is the world’s fastest deployment of the DeepSeek-R1 671B LLM to date.

Share

Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Articles
Microsoft reportedly set to cut thousands of jobs, with sales roles particularly at risk
Tech

Microsoft reportedly set to cut thousands of jobs, with sales roles particularly at risk

Microsoft reportedly set to lay off thousands in its new fiscal year...

Waymo looks to test its self-driving cars in New York
Tech

Waymo looks to test its self-driving cars in New York

Human drivers will remain at the wheel in Waymo self-driving cars once...

Justice at stake as generative AI enters the courtroom
Tech

Justice at stake as generative AI enters the courtroom

Generative artificial intelligence has been used in the US legal system by...