hardcoreufo

@hardcoreufo@lemmy.world

• ⁨Comment⁩ on ⁨Home server⁩ ⁨⁨5⁩ ⁨days⁩ ago⁩:

  Haha fair enough. Fixing it after the fact basically requires a second server of equal or greater storage. I fear a rebuild on my 16tb disks.

• ⁨Comment⁩ on ⁨Is anyone self-hosting their own AI?⁩ ⁨⁨6⁩ ⁨days⁩ ago⁩:

  Yes, I have a desktop with a radeon 9700 ai pro with 32GB of VRAM. Its more than doubled since I bought it but its basically a down clocked 9070xt with double the VRAM. I also have a little arc b50 in my server.

  Mostly yeah use it for privacy reasons. I run llama.CPP directly and access via open webui. I host a searx instance for it to use as web search. Mostly run qwen3.6/3.8 or gemma4 on the radeon and almost exclusively gptoss 20b on the B50 along with a second small model for tags and titles in open webui. Yeah I just use it mostly as a basic chatbot or as an agent in obsidian using the engram plugin. Helps search and summarize years of notes and works pretty well.

  I’ve tried to use it as a coding assistant in zed without much luck so usually just post my code into open webui for feedback and it works alot better for me.

  Yeah I can access it with other machines on my network including phone with conduit app. I can get to it on the go by connecting to home network with wireguard and sending a magic packet to wakeup desktop.

  I havent done any image gen nor have much use for it outside of maybe using it to make app icons in the style of papirus icons for programs they don’t and won’t support.

  It definitely feels more comprable to first ai wave than current frontier models but the privacy and price trade off is worth it to me. I’d say using it in obsidian has been the best use of it so far and one I certainly wouldn’t trust to an external AI.

• ⁨Comment⁩ on ⁨Home server⁩ ⁨⁨6⁩ ⁨days⁩ ago⁩:

  Raid z1 with 10 14tb disks? That’s a bold move cotton, let’s see how it plays out.

• ⁨Comment⁩ on ⁨⁩ ⁨⁨3⁩ ⁨months⁩ ago⁩:

  I’m in the September queue

• ⁨Comment⁩ on ⁨⁩ ⁨⁨3⁩ ⁨months⁩ ago⁩:

  Yeah I bought 2. Used one a bit but the other is unopened somewhere for future historians.

• ⁨Comment⁩ on ⁨NNN ended two days ago and I thought letting you all know this was important⁩ ⁨⁨2⁩ ⁨years⁩ ago⁩:

  How do you assert dominance over your rivals?

• ⁨Comment⁩ on ⁨Valve: don’t expect a faster Steam Deck ‘in the next couple of years’⁩ ⁨⁨3⁩ ⁨years⁩ ago⁩:

  They seem fine to me. Definitely a square profile if I run the test, but feel fine during gameplay to me. Probably the least worthwhile mod I’ve done though. The dbrand thumbstick grips are worth it.

• ⁨Comment⁩ on ⁨Valve: don’t expect a faster Steam Deck ‘in the next couple of years’⁩ ⁨⁨3⁩ ⁨years⁩ ago⁩:

  My deck is about to reach it’s final form and I need a few years out of it. So far I’ve done

  2TB ssd hall effect joysticks Transparent green shell front and back. played around with undervolting/ over clocking replaced screen with anti glare (only because I broke it)

  I’m waiting on a beefier heatsink and I’d like to find some cool buttons.

  The only other thing left to do would be try the 32GB RAM swap that some madlad did. I’m not really interested in the deck HD screen but could get behind a 800p or 1600p OLED panel.

• ⁨Comment⁩ on ⁨Don't use Proton Experimental for Baldur's Gate 3 (anymore)⁩ ⁨⁨3⁩ ⁨years⁩ ago⁩:

  That’s disappointing. Haven’t tested it on the deck yet as I’m waiting for new screen to arrive. It runs great on my moderate gaming PC with a 6600xt. Runs at 1080p ultra and hovers between 100 and 120fps. Usually closer to 120.