11 comments

  • simonw 57 minutes ago
    If you want to try out out the GGUFs from https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#th... be aware that you need Prism's llama.cpp fork to get them to work, from https://github.com/PrismML-Eng/llama.cpp/releases/tag/prism-...

    This should work:

      cd /tmp
    
      # Get the Prism macOS runtime
      curl -fL https://github.com/PrismML-Eng/llama.cpp/releases/download/prism-b10685-7dffb15/llama-prism-b10685-7dffb15-bin-macos-arm64.tar.gz -o bonsai-runtime.tar.gz
      tar -xzf bonsai-runtime.tar.gz
    
      # Get the ~5.95 GB GGUF model:
      curl -fL https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf/resolve/main/Ternary-Bonsai-2-27B-PTQ1_0.gguf -o Ternary-Bonsai-2-27B-PTQ1_0.gguf
    
      # Run the server, I used port 8331
      ./llama-prism-b10685-7dffb15/llama-server \
        -m Ternary-Bonsai-2-27B-PTQ1_0.gguf \
        --port 8331 -ngl 99 -fa on -c 32768
    
    Then open http://localhost:8331 for the (very good) baked in llama-server web UI... or run a prompt via the API like this:

      uvx llm openai endpoint http://127.0.0.1:8331/v1 \
        --model bonsai-2-27b --responses hi
    
    That's running at ~20 token/second for me on an M5 Pro (after a server restart I got 44 token/second, not sure why), but I'm pretty sure something isn't working right, on startup the server said "ggml_metal_device_init: - the tensor API is not supported in this environment - disabling".
    • simonw 17 minutes ago
      I used that to Generate an SVG of a pelican riding a bicycle:

      https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

      It took 18 minutes 20 seconds. Pretty decent for a 5.5GB model file.

      • kadoban 12 minutes ago
        Honestly looks pretty good except whatever is going on with its booty. Is that an ass helmet? I cannot parse what's going on there.
        • Forgeties79 4 minutes ago
          I think it’s supposed to be a wing
    • refibrillator 14 minutes ago
      Where did you get these instructions?

      They have a demo repo with a setup.sh script:

      https://github.com/PrismML-Eng/Bonsai-demo

      The release tag and weight file you suggest doesn’t match what they wrote.

      • simonw 3 minutes ago
        I figured them out, starting from the GGUF on Hugging Face.

        If you have found better instructions and they work then use those instead!

        Personally I prefer to download models directly rather than running some `./setup.sh` script where I need to then review what it does first.

    • OutOfHere 19 minutes ago
      Could you also note all this in a Discussion message at https://github.com/PrismML-Eng/llama.cpp/discussions ? Or are you only a HN person?
  • adrian17 24 minutes ago
    > Ternary Bonsai 2 27B uses ternary {−1, 0, +1} weights with FP16 group-wise scaling, for 1.76 effective bits per weight

    If I recall correctly, a recent post [1] has shown that Q2 quants (with like 2.6 bpw) of the same base Qwen model sit at the edge between "noticeably worse" and Q1's "useless". I took a quick glance at Bonsai's blog posts, and don't really see them comparing themselves to "typical" quants or explaining what's the special sauce that makes them better?

    https://news.ycombinator.com/item?id=49611128

    • edflsafoiewq 17 minutes ago
      I think the general idea is naive quantization falls apart below 4bpw but you can go lower with more sophisticated QAT-adjacent methods. Bonsai's quantization method is proprietary though.
    • 0x457 0 minutes ago
      [dead]
  • danbrooks 28 minutes ago
    Nice! Does anyone know how this compares to the Unsloth quantizations of this model? https://unsloth.ai/docs/models/qwen3.8#run-qwen3.8-guide
  • miffy900 48 minutes ago
    I really wish people would stop saying N times smaller than something when making a comparison; that makes no sense - it's 1/9th (11.11%) the size. You don't get a smaller quantity by multiplying by a number greater than 1.0. You could instead reverse the subjects being compared - "the original model is 9x bigger than this new smaller, efficient model" or some such. That makes sense.

    I keep seeing this being used when people talk about efficiency or performance gains and it's just very unintuitive language.

    • hamandcheese 41 minutes ago
      If we were talking about speed instead of size, i think it would be perfectly reasonable to say 9x faster. I'm not sure I agree that 9x smaller is unintuitive. It makes sense to me.
    • UI_at_80x24 41 minutes ago
      Me too!! It's a huge pet peeve. And it's so hard to get people to see how it's linguistically AND mathematically WRONG.
  • Aurornis 1 hour ago
    These are small enough that you can run them entirely in the browser https://huggingface.co/spaces/webml-community/ternary-bonsai...

    Remember to clear the downloaded weights afterward.

    Like the last model, it's amazing they work as well as they do. Use it for any longer task and they fall apart spectacularly and in interesting ways.

    • outofpaper 1 hour ago
      So you have some fun examples?
  • JonSchneider 59 minutes ago
    I'm hoping they release an 8B v2 based on the Qwen 3.8 series in the near future - that would give us a really powerful model that could be run directly on users phones.
    • sroussey 35 minutes ago
      Yes! And maybe get a hf fused webgpu runner for that model so it’s fast!
  • kamranjon 1 hour ago
    Love this for the folks with 16gb graphics cards - 3.8 27b has been incredible but not quite runnable on anything less than 32gb - will try loading this up on my 16gb intel b50 and see how it goes - not sure these quants can be accelerated by the XPU cores yet but maybe in time!
    • kadoban 1 hour ago
      You can run the ~4 bit quant(s) on 24gb, if you're not _too_ picky on context size.

      This will hopefully be better, though it'd be a _very_ surprising increase in performace at the size they say. Would love to see more about how it benchmarks.

      • spijdar 1 hour ago
        I run Unsloth's UD-Q4_K_S on 20 GB of VRAM (RX 7900 XT) and I get ~90k tokens of context without quantizing KV cache. With 8-bit quantization, I get about a 134k token context window. That's with only one slot, but for me, it works pretty darn well, with 20-35 tok/s depending on how full that window is.
  • logicallee 12 minutes ago
    (In case anyone remembers the compression post from yesterday[1], I checked and this one doesn't qualify for further compression - it's not zero-biased at all.)

    [1] https://news.ycombinator.com/item?id=49732931

  • abraxas 1 hour ago
    I'm not following the local mdoel scene too closely but this seems quite amazing. Is this able to be run on Apple silicon too?
    • Havoc 1 hour ago
      Their first 27B bonsai was able to run on an iphone.
    • kamranjon 1 hour ago
      "Ternary Bonsai 2 27B reaches up to 143 tokens/second on NVIDIA GeForce RTX 5090 and 46.8 tokens/second on M5 Max. On an RTX 4090, Ternary Bonsai 2 27B consumes just 0.714 mWh/token, making it 40% more energy-efficient than an 8B model running in full-precision."
      • pizza234 1 hour ago
        Their mention of the 5090 is bit odd, since on 32 GB GPUs, Q6 fits while having better quality. Very interesting model for 16 GB GPUs though!
        • sisve 53 minutes ago
          They mention 5090 with regards to speed, Q6 will not have that speed?

          And speed matters a lot for many use cases

          • selectodude 13 minutes ago
            150 tokens per second on a ternary model implies that it’s GPU bound, I’d bet a Q6 model is even faster because it’s existed longer and seen more optimization. You’d have to be insane to not run an NVFP4 quant over a ternary quant on Blackwell if they both fit.
      • azatom 40 minutes ago
        it is like "my fridge is 2mkm (millikilometer) from my desk" m=0.001 h=3600 it should be just Ws or just J
        • _kulang 29 minutes ago
          What’s wrong with milliwatt hours?
  • z2 1 hour ago
    I'd love to see a Bonsai model start with a 100B+ parameter model and get that down to <30 GB. But maybe at that point we call it Topiary?
  • 2001zhaozhao 38 minutes ago
    I think if they made this for Qwen3.8-Next it could fit in a single 5090?