Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • tried it out but based on the model sizing result i got i got an insufficient memory error when the server started running
    by jaylane
  • If you could post an issue if you still have the error around that would be awesome.
    by rhgraysonii
  • does this work similar to airllm? i am wondering how it would handle something like quantizing kimi k3 on a budget of 8 gbs, or is that something you are not attempting to solve yet?
    by mbuchel-hn
  • Yes that is exactly what this does.
    by rhgraysonii
  • The project name is perfect!
    by sscarduzio
  • This is really impressive. Can you say a bit about the underlying process? I'm guessing this is post-training qantization? Isn't PTQ also resource-intensive? (Ie might not work on any machine)
    by puttycat
  • I gotta laugh at some of the models it suggests, for example:

    > AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUF

    you’re telling me you managed to fit Fable 5 into just 4B?

    by jedbrooke
  • Fyi that model name to me reads

    Qwen3 4b params distilled/trained with fable 5

    by mannyv
  • Reminds me of https://github.com/AlexsJones/llmfit
    by hmokiguess
  • LLMFit tells you what can run on something. I built something quite similar to their search into Shoehorn now.
    by rhgraysonii
  • This is interesting. I wonder how it could work with something like https://github.com/JustVugg/colibri.
    by akshay_akula