AI Dynamics

Global AI News Aggregator

Qwen 2.5 Models Achieve Impressive Token Generation Speeds

By

@sambanovaai

–

Shout-out to @ArtificialAnlys for independently verifying our speeds! 225 tokens/sec on Qwen 2.5 72B
566 tokens/sec on Qwen 2.5 Coder 32B @Alibaba_Qwen @_micah_h #AI #GenAI #LLM

→ View original post on X — @sambanovaai,

Commentaires

Leave a Reply

Your email address will not be published.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

MORE ARTICLES