Get the latest tech news

Llamafile 0.8 Releases With LLaMA3 & Grok Support, Faster F16 Performance


Llamafile has been quite an interesting project out of Mozilla's Ocho group in the era of AI

Llamafile builds off Llama.cpp and makes it easy to ship an entire LLM as a single file with both CPU and GPU execution support. Mixture of Experts (MoE) models like Mixtral and Grok are also now 2~5x faster for executing on CPUs after refactoring the tinyBLAS CPU code. I'll be working on new Llamafile benchmarks soon.About The AuthorMichael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience.

Get the Android app

Or read this on Phoronix

Read more on:

Photo of releases

releases

Photo of Grok

Grok

Photo of llama3 &

llama3 &

Related news:

News photo

Rise of the Ronin is the dark horse of the March 22 releases | Kaser Focus

News photo

Elon Musk’s Grok keeps making up fake news based on X users’ jokes | X likely hopes to avoid liability with disclaimer that Grok "can make mistakes."

News photo

US releases sealed Brazil orders to X, shedding light on account suspensions