professorpalmer /
bonsai-ada-surgery
Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternary weights. Windows bundle + receipts.
Updated 40 min ago
Why now
Version bundle-20261026 came out on October 27.
+5 stars gained this week
Stars gained each day, last 30 days
Usual pace · 3 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A Windows launcher and patched llama.cpp server that runs PrismML's ternary Bonsai 2 27B model with a full 262k context on 12 GB and 8 GB NVIDIA cards. It is for people running local LLMs on consumer GPUs.
Summary written by AI from the repository’s description and README.
professorpalmer / bonsai-ada-surgery
View on GitHub(opens in new tab)