this post was submitted on 28 May 2026
30 points (100.0% liked)

Boycott US

2534 readers
179 users here now

Overview:

The community dedicated to boycotting the US until they stop fascism, restore full democracy and start following international law.

Americans have a moral obligation to resist Donald Trump and project 2025 at every turn.

America is a flawed democracy currently being ruled by oligarchs. Stop the backslide! Dont let America become the next Hungary.

America needs to challenge the court rulings of citizens united v. fec and shelby county v. holder, protect the media, implement independent district drawing, and the single transferable vote so they don't end up having people stay home in life-changing elections because they cannot vote for their favourite candidate.

Join 50501.chat to fight back!


Related communities:

Boycott:!buycanadian@lemmy.ca

!buyeuropean@feddit.uk

!boycott@lemmy.sdf.org

!boycottchina@sopuli.xyz

Activism:!antitrumpalliance@lemmy.world

!petitions@lemmy.ca

!palestine@lemmy.dbzer0.com

!protest@lemmy.world

!israelicrimes@lemmy.world

!patriotsforprogress@lemmy.ca

!goodsuniteus@lemmy.ca


founded 1 year ago
MODERATORS
 

Has anyone tried in organization to use self hosted llm models for agentic programming?

Im curious if it makes any sense. My organization spends fortune on tokens from US companies. I want to recommend something… I think that will be cheaper to use it on own machines instead…

you are viewing a single comment's thread
view the rest of the comments
[–] panda_abyss@lemmy.ca 6 points 1 month ago

So self hosting is still not great.

The big problem is you can get large memory but slow prompt processing, which reduces your context window, or you can get semi-fast GPU with low memory, where you’re capped on models.

Sometimes I run pi agent in a container with Gemma 4 or Qwen 3.6, but even on strix halo after 60k tokens the quadratic slowdown is brutal.

We aren’t there yet for complex agaentic workflows locally, and it’s primarily a hardware issue.

Though innovations in performance are being shipped regularly, they’re incremental.