11 comments

  • thomasjb 0 minutes ago
    I've been watching and waiting for this, interested to see how smart it is, as it fits with my interest of getting the smartest possible model running in 10GB of VRAM (RTX3060 that has to drive 2 monitors and run an llm)
  • sigbottle 3 minutes ago
    What's the hiring space and business strategy around all of these smaller AI labs? Its really cool that people like these guys get paid to optimize models and give them out for free (open source). Do a lot of these labs have forward deployed engineers doing integrations with customers who want local models? Is there a general shift towards the local model crowd?
  • syntaxing 5 minutes ago
    I don’t know if the llama cpp implementation is wonky (and only supports the binary version) but it’s a lot slower than 35B-A3B @ Q4_KM + MTP with CPU offloading.
  • liuliu 51 minutes ago
    The problem, of course, is if you run the UD_Q2 variant (Unsloth) which does only post-training, the number is pretty close to 1-bit model here and the 5% drop in tool-call is significant than it suggests in real-life use cases.
    • liuliu 41 minutes ago
      You also need to pay close attention to BFCLv3 multi-turn result, that helps you to get a sense how frequently these quants will be in a doom loop.
  • simonw 37 minutes ago
    The models themselves are showing up on Hugging Face here: https://huggingface.co/prism-ml/models
  • syntaxing 20 minutes ago
    For those curious about their demo, I’m pretty sure it’s using Locally AI (iOS only) that lmstudio acquired/aquihired a couple months ago.
  • alvatech 58 minutes ago
    TIL that 1 bit models are actually 1.58 bit with three values +1, 0 and -1
    • NitpickLawyer 36 minutes ago
      There's two variants of this (or, as the joke goes, for very big values of bit):

      Ternary Bonsai 27B uses ternary {−1, 0, +1} weights with FP16 group-wise scaling, giving a true 1.71 effective bits per weight.

      1-bit Bonsai 27B uses binary {−1, +1} weights with the same group-wise scaling, giving 1.125 effective bits per weight.

    • bensyverson 48 minutes ago
      Yeah, it's an unfortunate convention from the very first "1 bit" model. But to be clear, Bonsai comes in both ternary and actual 1-bit variants.
  • erelong 19 minutes ago
    I was trying Ornith 9B locally (it's up on Ollama) which claims:

    > Ornith-1.0-9B, which can be easily deployed on edge devices, matches or exceeds the performance of much larger models such as Gemma 4-31B and Qwen 3.6 35B.

    https://deep-reinforce.com/ornith_1_0.html

    Only tried it so much so far; it did a little better than Qwen 9B

    • janalsncm 5 minutes ago
      Is that a 1-bit LLM? I don’t understand the connection with this article.
    • liuliu 17 minutes ago
      Note that 3.5 9B cannot do thinking (while 3.6 27B can, pretty effectively, quite verbosely).
  • xyzsparetimexyz 30 minutes ago
    That's awesome. What's the largest model that could fit onto a single 16gb gpu at 1.125 effects bits per weight?
  • Havoc 39 minutes ago
    This must be some sort of unpublished app?

    I can just see their image tool on the app store

  • ai_fry_ur_brain 41 minutes ago
    [dead]