• @brucethemoose@lemmy.world
    link
    fedilink
    English
    020 days ago

    Its a lower midrange only launch like it appears to be, it will be extremely unprofitable. AMD may even eat large chunks of this market with the Strix Halo APU, which could be similar to the B570 with no need for a discrete GPU.

    Theres actually a big and growing demand for ANY high VRAM GPU for the LLM crowd (that AMD is ignoring for inexplicable reasons beyond Strix Halo) but it appears Intel can’t even compete there. No 256 bit APU, their GPU is 192 bit so capped at like 24GB…

    • @rumba@lemmy.zip
      link
      fedilink
      English
      020 days ago

      Intel is totally missing the boat honestly. Their mobile i9 with the built-in GPU can share DDR5 with the video card.

      You can put 96 gigs of RAM in a small form factor and load in a monster model. It’s not super fast, But it works, and it’s a lot faster than not offloading layers off the CPU.

      They should be selling nuk sized PCs with built-in graphics and 128 gigs of the fastest RAM they can put on the boards.

      • @brucethemoose@lemmy.world
        link
        fedilink
        English
        019 days ago

        IMO its not really “enough” until the bus is 256 bit. Thats when 32B-72B class models start to look even theoretically runnable at decent speeds.

          • @brucethemoose@lemmy.world
            link
            fedilink
            English
            0
            edit-2
            19 days ago

            Also that is a very low context test. A longer context will bog it down, even setting aside the prompt processing time.

            …On the other hand, you could probably squeeze a bit more running openvino instead of llama.cpp, so that is still respectable.

            • @rumba@lemmy.zip
              link
              fedilink
              English
              019 days ago

              text test. A longer co

              yeah, it’s definitely not good enough for user-facing work, but if I’m working on development for something like translations, being able to see the 70b output to compare it to other models, it’s super useful before I send it off to something that costs more money to run.

              9/10 times, the bigger model isn’t significantly better for what I’m trying to do, but it’s really nice to confirm that.