8 comments

  • mmastrac 1 minute ago
    Is it just me or does this post not mention how much RAM they had? I would love to know - I have a dual-Xeon 1U screamer with 96GB of DDR4 RDIMM just sitting around...
  • hparadiz 29 minutes ago
    Here's my report running several different models on a dual Xeon with 256 GB of DDR4 and no GPU.

    https://gist.github.com/hparadiz/f3596d00a62d8ebb2dadcc46ee5...

    • puzzlingcaptcha 2 minutes ago
      Have you tried with a single CPU to get rid of the NUMA penalty? I understand this likely means halving the memory but I am interested in how much of a difference it makes
    • neomindryan 17 minutes ago
      Thank you for sharing!
  • throwaway2027 57 minutes ago
    That's quite slow I'm getting 8-12 t/s on a 13 year old CPU. (Speed varies by context size and other settings who knows)

    https://news.ycombinator.com/item?id=48354801

    • neomindryan 17 minutes ago
      Thank you for sharing / linking!
  • neomindryan 1 hour ago
    Author here, it looks like my original comment was flagged for some reason. The fix is open upstream as PR #2138 (https://github.com/ikawrakow/ik_llama.cpp/pull/2138)
  • ChrisArchitect 22 minutes ago
    Related:

    A 10 year old Xeon is all you need

    https://news.ycombinator.com/item?id=48353348

  • rvba 21 minutes ago
    Sorry for asking here but literally nobody knows:

    Android studio connected to a local model disconnects automatiacally after 10 minutes. How set this limit to 12 hours or remove it completely?

    I could run my LM studio model all night... but I cant, since Android studio times out after a hard limit of 10M.

    This is not related to number of tokens. I do 130 sec.

  • neomindryan 1 hour ago
    Author here. The short version: a viral post ran Gemma 4 on a 2016 Xeon; my Xeons are 2013, and the fork it used assumes AVX2, which Ivy Bridge doesn't have. The build failure was easy. The fun bug was the silent one: two MoE graph ops with no dispatch case on non-AVX2 builds, so every expert FFN output was uninitialized memory. Deterministic, NaN-free, fluent-looking multilingual gibberish.

    The fix is open upstream as PR #2138 (https://github.com/ikawrakow/ik_llama.cpp/pull/2138), awaiting review. Fair warning on the AI angle: the patch was written by Claude at my direction. The post is explicit about which parts were me and which weren't. Happy to answer questions about either the bug or the workflow.

    • otherjason 41 minutes ago
      This reads as pretty clearly AI-generated text, which is against HN guidelines.
      • pkghost 22 minutes ago
        Here's the thing: life also imitates art. If you invert your load-bearing assumption, it could be that he just reads too much slop. But my honest take? You might be right.
  • aniwalunj 1 hour ago
    Truly amazing. This gives a peek into the future for what's possible.