Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Groq Inc. has announced that Llama3, a smaller and faster AI model, has become its most popular model within 48 hours of release. The model's reduced size and increased speed make it highly suitable for various types of hardware, enhancing its appeal to developers. Additionally, Poe platform now supports Groq-powered inference for Llama 3, offering the Llama-3-70b-Groq model with near-instant streaming capabilities.
Llama3 is really disruptive because it is a much smaller model, so it's much easier to run on all types of different hardware, and much faster. Those two things are like catnip for developers. Within 48 hours it became the most popular model that we run on Groq. The use cases…
Llama3 is really disruptive because it is a much smaller model, so it's much easier to run on all types of hardware, and much faster. Those two things are like catnip for developers. Within 48 models it became the most popular model that we run on Groq. https://t.co/TyDvYeRQNw
Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2) https://t.co/F6bXca7LoH
