‹ BackHN Continuity

Thread

Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

589 points · 200 comments · JonSchneider

  1. simonw · · focus · HN ↗
    If you want to try out out the GGUFs from <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;prism-ml&#x2F;Ternary-Bonsai-2-27B-gguf#these-files-need-our-llamacpp-build" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;prism-ml&#x2F;Ternary-Bonsai-2-27B-gguf#th... be aware that you need Prism&#x27;s llama.cpp fork to get them to work, from <a href="https:&#x2F;&#x2F;github.com&#x2F;PrismML-Eng&#x2F;llama.cpp&#x2F;releases&#x2F;tag&#x2F;prism-b10685-7dffb15" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PrismML-Eng&#x2F;llama.cpp&#x2F;releases&#x2F;tag&#x2F;prism-...

    This should work:

      cd &#x2F;tmp

  # Get the Prism macOS runtime
  curl -fL https:&#x2F;&#x2F;github.com&#x2F;PrismML-Eng&#x2F;llama.cpp&#x2F;releases&#x2F;download&#x2F;prism-b10685-7dffb15&#x2F;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:&#x2F;&#x2F;huggingface.co&#x2F;prism-ml&#x2F;Ternary-Bonsai-2-27B-gguf&#x2F;resolve&#x2F;main&#x2F;Ternary-Bonsai-2-27B-PTQ1_0.gguf -o Ternary-Bonsai-2-27B-PTQ1_0.gguf

  # Run the server, I used port 8331
  .&#x2F;llama-prism-b10685-7dffb15&#x2F;llama-server \
    -m Ternary-Bonsai-2-27B-PTQ1_0.gguf \
    --port 8331 -ngl 99 -fa on -c 32768
    Then open http:&#x2F;&#x2F;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:&#x2F;&#x2F;127.0.0.1:8331&#x2F;v1 \
    --model bonsai-2-27b --responses hi
    That&#x27;s running at ~20 token&#x2F;second for me on an M5 Pro (after a server restart I got 44 token&#x2F;second, not sure why), but I&#x27;m pretty sure something isn&#x27;t working right, on startup the server said &quot;ggml_metal_device_init: - the tensor API is not supported in this environment - disabling&quot;.
    1. francisjp · · focus · HN ↗
      Thanks for all of your exploration in public Simon.

      Commenting because the fix I proposed was merged in roughly 49 commits after the PrismML Fork. The “tensor API is not supported” warning occurred because llama.cpp’s startup probe fails to compile a matmul2d kernel: Metal’s tensor headers require language version 4.0, but ggml-metal-device.m previously omitted MTLCompileOptions.languageVersion, disabling the API universally.

      Here’s a link to the diff if you want to try and update that fork to take advantage of the prefill gains afforded by the hardware: <a href="https:&#x2F;&#x2F;github.com&#x2F;ggml-org&#x2F;llama.cpp&#x2F;pull&#x2F;27461&#x2F;changes" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ggml-org&#x2F;llama.cpp&#x2F;pull&#x2F;27461&#x2F;changes

      1. jb_briant · · focus · HN ↗
        That kind of issue is exactly why Im so happy to have LLMs, let it take one hour or trial and error instead of me spending a day digging traces
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.