If even half of Intel’s claims are true, this could be a big shake up in the midrange market that has been entirely abandoned by both Nvidia and AMD.

  • brucethemoose@lemmy.world
    link
    fedilink
    English
    arrow-up
    6
    ·
    edit-2
    19 days ago

    If they double up the VRAM with a 24GB card, this would be great for a “self hosted LLM” home server.

    3060, 3090 prices have been rising like crazy because Nvidia is vram gouging and AMD inexplicably refuses to compete. Even ancient P40s (double vram 1080 TIs with no display) are getting expensive. 16GB on the A770 is kinda meager, but 24GB is the point where you can fit the Qwen 2.5 32B models that are starting to perform like the big corporate API ones.

    And if they could fit 48GB with new ICs… Well, it would sell like mad.

    • Psythik@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      19 days ago

      I always wondered who they were making those mid- and low-end cards with a ridiculous amount of VRAM for… It was you.

      All this time I thought they were scam cards to fool people who believe that bigger number always = better.

      • brucethemoose@lemmy.world
        link
        fedilink
        English
        arrow-up
        4
        ·
        19 days ago

        Also “ridiculously” is relative lol.

        The Llm/workstation crowd would buy a 48GB 4060 without even blinking, if that were possible. These workloads are basically completely vram constrained.

    • Fedegenerate@lemmynsfw.com
      link
      fedilink
      English
      arrow-up
      0
      ·
      edit-2
      19 days ago

      An LLM card with quicksync would be the kick I need to turn my n100 mini into a router. Right now, my only drive to move is that my storage is connected via usb. SATA is just not enough value for a whole new box. £300 for Ollama, much faster ml in immich etc and all the the transcodes I could want would be a “buy now figure the rest out later” moment.

      • brucethemoose@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        19 days ago

        Oh also you might look at Strix Halo from AMD in 2025?

        Its IGP is beefy enough for LLMs, and it will be WAY lower power than any dGPU setup, with enough vram to be “sloppy” and run stuff in parallel with a good LLM.