Bonsai 2 is Prism ML’s ternary-weight family. This guide uses the compressed Ollama download; publisher MLX packs have different sizes and runtime requirements.
Where it works well
- Compact ternary weights.
- Text and image input.
- Optional reasoning in supported runtimes.
Common use cases
- Draft a caption from a clear photo.
- Summarize a short passage.
- Compare ideas using facts you provide.
Know its limits
- Use current Ollama with Bonsai 2 support; older GGUF loaders may not support the ternary format.
- The download is not total running memory; vision components and context add overhead.
- The advertised context ceiling does not mean it fits at the listed RAM estimate.
Run it on your computer
Compatibility: Use a current runtime with Bonsai 2 ternary support.
Start with a compressed download and a short conversation. Our estimate is about 24 GB of total RAM or Mac unified memory, with room for the operating system. The listed 8.3 GB download is the model file, not its full running memory use.
Check the model’s supported runtime and hardware before loading it. System RAM on a PC and unified memory on a Mac are different from dedicated NVIDIA VRAM. A memory match doesn’t guarantee compatibility or speed. Choose a smaller model if responses are too slow.
Use a desktop app that supports the listed model format, such as LM Studio or Ollama. Download the exact local variant, load it in Chat, and start with one small task. Model downloads need internet; local chat can work offline once the model is downloaded.
Official model information
Model capabilities checked October 2026. The use cases above are practical starting suggestions, not performance guarantees.