---
title: "Open source AI needs cheap local speed"
date: 2026-07-01
canonical: https://solmaz.io/x/2072271038801711362/
x_url: https://x.com/onusoz/status/2072271038801711362
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

I keep seeing insanely expensive builds giving insanely impressive results

These results don't matter

What matters is, whether one can:

- run a "SOTA level" model, whatever that is
- with under 32gb VRAM or unified memory
- in 5 parallel sessions
- with 50~100 tok/s each
- with enough leeway memory for other applications
- in a system as cheap as $1000

That is our goalpost

That is the threshold when open source AI will win

*Quotes a post by @LottoLabs (https://x.com/LottoLabs/status/2071782167085289843); its text is omitted here because it is not covered by this site's license.*