Ternary Bonsai 2

Hold to start

27B ternary weights · 5.9 GB download, cached after the first visit

~9.3× smaller than FP16 · 98.2% of FP16 intelligence retained

Loading model

0%

Private preview

Ternary Bonsai 2 is
not public yet.

Paste a Hugging Face access token with read access to the model repo. It stays in this browser — requests go only to huggingface.co.

Ternary Bonsai 2 27B Prism ML Ready

What is on your mind?

27 billion parameters at ternary precision, decoded by WebGPU kernels on your own GPU. Nothing you type leaves this machine.

Runs fully on-device