solstone support

what your machine needs to think locally

solstone 2026-11-21 17:02:12

what your machine needs to think locally

by default, your journal is processed on your own device: no cloud, nothing to configure. that takes real memory, and on linux and windows a GPU. this page lays out the bar, and what happens if your computer doesn't clear it.

the floor

| platform | requirement | |---|---| | apple silicon (mac) | 16 GB of memory | | intel mac | not supported. the journal and the solstone app are both for apple silicon macs: use one, or run the journal on supported linux instead | | linux | a supported GPU (amd, nvidia, or intel) with at least 6 GB of GPU memory | | windows | a compatible GPU with at least 6 GB of GPU memory, the same bar as linux. see getting solstone on windows for setting up local there. bring your own model works there as well, and you can still pair the solstone app on windows with a journal on a mac or linux machine instead. with journal 2.0.64 or later, a windows arm64 pc is checked against the same bar, though local thinking hasn't been tested on an arm64 GPU |

the journal checks the computer it runs on during setup. with journal 2.0.43 or later, installing local thinking on a computer known to be below the bar also stops before the local thinking model downloads, and tells you why.

if your machine can't clear the bar

nothing breaks. you just pick a different way to process your journal:

see three ways to process your journal for the full picture.

still not sure?

on the computer your journal runs on, open your journal and go to its thinking app to choose how your journal is processed. or see how much of your computer's memory your journal uses for the full picture.