Re:I want everything local – Building my offline AI workspace
by varenc on Friday August 08, 2025 @11:14PM
(#44843764)
> You already need very high end hardware to run useful local LLMs
A basic maxbook can run gpt-oss-20b quite easily and it's quite useful for many tasks. And fast. Of course Macs have a huge advantage for local LLMs inference due to their shared memory architecture.
A basic maxbook can run gpt-oss-20b quite easily and it's quite useful for many tasks. And fast. Of course Macs have a huge advantage for local LLMs inference due to their shared memory architecture.