On Thu, Apr 16, 2026 at 2:10 PM George M. Rimakis <[email protected]>
wrote:

> $20/mo will buy you a ChatGPT subscription which I think is more than
> adequate for any M100 project.
>
> The size of whatever project you are working on, by virtue of it being
> designed for a small system, will fit in the models context window. Plus
> whatever other context you need to provide.
>
> Maybe you can fine tune Gemma 4 or something to run locally, but I’m
> pretty sure it will cost you much more than $20 a month, and won’t be as
> good as Codex.
>
> But honestly if you want to do it just to do it, that’s a totally
> different story :D
>
> There isn’t a ton of practicality in tinkering with these old machines
> anyway, just for fun.
>
> -George
>
>
Yeah I have had odd behaviors from Gemini. Like it gets tired and cranky
and starts making up excuses to not do things. I have a free subscription
since i take some college classes and they offer free access. But it just
refuses to work sometimes, I don't know if it is trying to limit compute
cycles.

For me it's really about a) learning to do it and b) being able to share a
good / cheap/ reusable system with the community focused on our devices.

-- John.

Reply via email to