4 comments

  • chilipepperhott 1 hour ago
    For those that care, this blog post was clearly authored by an LLM.
    • ge96 58 minutes ago
      Ahhhh I always feel like I was owned when I find that out, I was skimming through it like "wow this is a lot, this is a long blog post"
  • danielrmay 1 hour ago
    Solid analysis, these quotes were particularly damning imo:

    "You don’t accidentally forget to disclose that your memory is split into two non-unified pools. That’s a deliberate omission of the single most important architectural limitation of the device."

    "Read that filename. layer_27_36. That’s not dynamic hot neuron routing, that’s static layer assignment"

  • ricardobeat 1 hour ago
    To the author’s point, I was able to run Qwen3.5 122B at close to 20 tokens/s on a Ryzen AI Max 395+ mini PC with 128GB (64/64 split, for some reason it needs a lot of system RAM).
  • jauntywundrkind 1 hour ago
    New meaning to the words "hot pocket", given how toasty that Cix CD8180 is!

    And that's at idle!! (15w) https://www.jeffgeerling.com/blog/2025/minisforum-stuffs-ent...

    Now add two NPUs. Personally I'm for it. But it is going to need quite the cooling. A bunch of Frore Airjet mems devices?

    • gravelturnip88 43 minutes ago
      Based on the exploded views I found and some text references in a product page or something I can't quite remember it uses a vapor chamber and a dual fan configuration. If you go frame by frame on the exploded view animation it can be seen.