Thread

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

589 points · 200 comments · JonSchneider

simonw · 1789683185 · focus · HN ↗
If you want to try out out the GGUFs from <a href="https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#these-files-need-our-llamacpp-build" rel="nofollow">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 <a href="https://github.com/PrismML-Eng/llama.cpp/releases/tag/prism-b10685-7dffb15" rel="nofollow">https://github.com/PrismML-Eng/llama.cpp/releases/tag/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://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'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".
1. wombat23 · 1789725211 · focus · HN ↗
  I managed to run it with RTX 3070 (8GB VRAM) following the "Quickstart" on HF model card with minor modifications (modify the architecture 86 for your own hardware):
  git clone https://github.com/PrismML-Eng/llama.cpp && cd llama.cpp cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=86 && cmake --build build -j
  Then downloaded & verified `Ternary-Bonsai-2-27B-PTQ1_0.gguf` from HF and ran
  ./llama.cpp/build/bin/llama-cli -m Ternary-Bonsai-2-27B-PTQ1_0.gguf -ngl 99 -fa on -c 32768 -b 256 -ub 64 --temp 1.0 --top-p 0.95 --top-k 20 -ctk q8_0 -ctv q8_0 -p "hello world in x86 assembler" -n 256
  the parameters were suggested by gpt-5.6-luna to reduce memory footprint, as the defaults ran OOM on my gpu. result looks good:
  [ Prompt: 165.6 t/s | Generation: 40.6 t/s ]
  would be nice if they upstreamed their changes so that it runs with the original llama.cpp
  1. zepearl · 1789743082 · focus · HN ↗
    Exact same test executed on my RTX 3060 (12 GiB VRAM, PCIe 3.0 4x slot):
    [ Prompt: 95.0 t/s | Generation: 26.5 t/s ]
    (the test's prompt is very short but with longer ones the I get ~200 prompt processing rate, but I was hoping for a better token generation rate...)
    Am I understanding correctly that no draft model exists (will never exist or just currently does not exist yet)?
    There is no draft file in Huggingface's repository ( <a href="https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf/tree/main" rel="nofollow">https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf/tr... ) and in the file "scripts/download_models.sh" of the demo repository ( <a href="https://github.com/PrismML-Eng/Bonsai-demo/blob/main/scripts/download_models.sh" rel="nofollow">https://github.com/PrismML-Eng/Bonsai-demo/blob/main/scripts... ) I see this remark:
    if [ "$_family" = "bonsai2" ]; then the projector ships in the same repo; Bonsai 2 has no dspark drafter

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.