14 comments

  • sigbottle 27 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?
  • erwan577 5 minutes ago
    The KV-cache memory usage also seems remarkably frugal, even at the full context length. That could make this model particularly useful in multi-agent coding workflows.

    I wish KV-cache memory usage and related optimizations were discussed more clearly in new model announcements and demos.

  • kristianp 12 minutes ago
    Apparently Apple is "in talks" with the PrismML: https://www.cnbc.com/2026/07/14/apple-prismml-ai-compression...
  • liuliu 1 hour 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 1 hour 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.
  • luckystarr 11 minutes ago
    Tried it on Android and got "!!!!!!!!!!!!!" for answers.
  • syntaxing 44 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.
  • simonw 1 hour ago
    The models themselves are showing up on Hugging Face here: https://huggingface.co/prism-ml/models
  • syntaxing 30 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.
    • pulse7 13 minutes ago
      Most probably not optimized yet for this model...
  • thomasjb 24 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)
  • alvatech 1 hour ago
    TIL that 1 bit models are actually 1.58 bit with three values +1, 0 and -1
    • NitpickLawyer 1 hour 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 1 hour 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 43 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

    • liuliu 42 minutes ago
      Note that 3.5 9B cannot do thinking (while 3.6 27B can, pretty effectively, quite verbosely).
    • janalsncm 29 minutes ago
      Is that a 1-bit LLM? I don’t understand the connection with this article.
  • xyzsparetimexyz 54 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?
    • Catloafdev 18 minutes ago
      Doing some naive math, the F16 filesize is ~53.8gb, the 1-bit version is ~3.8gb, about 7% of the original size. The F16 size is roughly 2x param count, so that gives a rough ballpark of ~110B.
  • Havoc 1 hour ago
    This must be some sort of unpublished app?

    I can just see their image tool on the app store

  • ai_fry_ur_brain 1 hour ago
    [dead]