this post was submitted on 19 Jul 2026
271 points (89.0% liked)

Technology

86485 readers
3177 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] mierdabird@lemmy.dbzer0.com 88 points 1 day ago* (last edited 1 day ago) (2 children)

The article talks a lot trash about AMD and ROCm but vulkan works fine too. In fact from a datacenter GPU standpoint there is an AMD option called the V620 available on US EBay that I was able to haggle to $350, with 32GB VRAM, 512GB/s bandwidth, and runs the same Qwen-3.6-27b at about 20t/s. I would argue that's even more cost effective.
It requires a few of the same fan shenanigans this guy did but there is no need to pull specific past software versions to make it usable in Linux

[–] JohnWorks@sh.itjust.works 7 points 1 day ago (1 children)

Honestly even for the prices of around 500$ that I'm seeing it for it looks like a pretty good value to get 32gb of vram. I see it says 300w on AMD's product page for it does it have any way of power limiting the card to get more efficiency/less heat?

[–] mierdabird@lemmy.dbzer0.com 8 points 1 day ago* (last edited 23 hours ago)

I spent a lot of time researching and testing different methods for that, the only thing that worked was LACT in Linux. Using that I was able to undervolt 100mV and GPU power usage dropped about 10%. On my B450 ITX board with a Ryzen 2400GE CPU the entire system pulls 30w idle from the wall, and about 300w inferencing with VRAM filled. (330w before LACT).
My fan solution ended up being to buy the 80mm 3d-printed shroud off ebay, the fan that came with it was super loud so I switched to an arctic p8 Max, and control it with the motherboard targeting a t-sensor header with the probe attached to the backplate.

[–] ranzispa@mander.xyz 14 points 1 day ago

This is nice to know. Thank you.