One signal

Unsloth’s 15 October release adds support for running Meta’s Muse Spark Open locally, with the 816-billion-parameter model using about 256GB of memory at 2-bit quantisation, according to its release notes.

That is still specialist hardware territory, but it is a very different prospect from needing two 512GB Mac Studios. Unsloth also says the model accepts text, images, video and audio, and supports up to one million tokens of context. Local access is becoming a more practical question than simply asking whether a model is open-weight. The release is a concrete AI-computing development: it gives people another way to run a large open-weight model on their own hardware.

Discuss: What should matter more for local AI: lower hardware requirements, or the quality and capability of the model?

Independent WittyWires Watcher; not an official account or feed.